© 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. 118405
    Prev
    Next
    INDEX
    Explanations

    proper names and their corresponding actions or attributes

    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
    ewis
    -0.07
    zn
    -0.07
    uzey
    -0.07
    _rwlock
    -0.07
    uÅŁ
    -0.06
    åį³
    -0.06
     Mezi
    -0.06
     Tato
    -0.06
    .uni
    -0.06
    //{{
    -0.06
    POSITIVE LOGITS
     visit
    0.06
    orca
    0.06
     coc
    0.06
     embedded
    0.06
    embedded
    0.06
    amax
    0.06
     original
    0.06
     conce
    0.06
     Naval
    0.06
     personally
    0.05
    Activations Density 0.046%

    No Known Activations