© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 29-LLAMASCOPE-RES-32K
    11. 15404
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "com" in various contexts, suggesting a focus on elements related to communications or components associated with the prefix "com" in programming or technical documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bernardino
    -0.16
    -0.15
    _traits
    -0.14
     competit
    -0.14
    [
    -0.14
    "crypto
    -0.13
    ugged
    -0.13
     relative
    -0.13
    isen
    -0.13
    e
    -0.13
    POSITIVE LOGITS
    .example
    0.22
    .syntax
    0.17
    _example
    0.17
    .***.***
    0.16
    example
    0.16
    .sulake
    0.16
    .company
    0.16
     пÑĢимеÑĢ
    0.16
    .skill
    0.16
    èŃ
    0.15
    Activations Density 0.017%

    No Known Activations