© 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. 17-LLAMASCOPE-RES-131K
    6. 78155
    Prev
    Next
    INDEX
    Explanations

    articles and quantifiers related to descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    st
    -0.09
    ir
    -0.08
    e
    -0.07
    bid
    -0.07
    .wik
    -0.07
    stoup
    -0.07
    th
    -0.07
    z
    -0.06
    à¸ķ
    -0.06
    .decorate
    -0.06
    POSITIVE LOGITS
     lot
    0.08
     few
    0.08
    Forge
    0.07
     certain
    0.07
    onda
    0.07
    ustralian
    0.07
    eron
    0.07
    uteur
    0.07
    /an
    0.06
    iyim
    0.06
    Activations Density 1.563%

    No Known Activations