© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 25-LLAMASCOPE-RES-32K
    11. 18301
    Prev
    Next
    INDEX
    Explanations

    mathematical or notation-related symbols and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aits
    -0.17
    305
    -0.15
    éal
    -0.14
    itur
    -0.14
     renew
    -0.13
    ç½²
    -0.13
     symb
    -0.13
    icros
    -0.13
    gos
    -0.13
    lsruhe
    -0.13
    POSITIVE LOGITS
    _{
    0.17
    QUOTE
    0.15
    ened
    0.14
    .Modules
    0.13
    .metamodel
    0.13
    apr
    0.13
    ungen
    0.13
    loo
    0.13
    quot
    0.13
    Esp
    0.13
    Activations Density 0.031%

    No Known Activations