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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-32K
    6. 9152
    Prev
    Next
    INDEX
    Explanations

    placeholders for missing words or blanks in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ampie
    -0.14
    .toByteArray
    -0.14
    aml
    -0.14
    _Enter
    -0.14
    ahun
    -0.14
    seealso
    -0.13
    .Formatter
    -0.13
    .toJSON
    -0.13
    edy
    -0.13
    gaard
    -0.13
    POSITIVE LOGITS
    ptom
    0.17
    [
    0.16
    mage
    0.16
    nia
    0.15
    ellar
    0.15
    218
    0.15
    ela
    0.14
     horn
    0.14
     Jones
    0.14
    urr
    0.14
    Activations Density 0.008%

    No Known Activations