Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 71252
    Prev
    Next
    INDEX
    Explanations

    instructions or guidance related to navigation or searching

    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
    yro
    -0.06
    erver
    -0.06
     Paths
    -0.06
    fst
    -0.06
     Gale
    -0.06
     Tomorrow
    -0.06
    via
    -0.06
    zap
    -0.06
    opath
    -0.06
     paths
    -0.06
    POSITIVE LOGITS
    gnore
    0.09
    .Monad
    0.07
    orr
    0.07
    :@""
    0.07
     PMID
    0.07
    RPC
    0.06
    .idea
    0.06
     merged
    0.06
    npj
    0.06
    *this
    0.06
    Activations Density 0.002%

    No Known Activations