© 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. 15-LLAMASCOPE-RES-131K
    11. 732
    Prev
    Next
    INDEX
    Explanations

    documentation comments in code

    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
    stown
    -0.06
    lant
    -0.06
    ıy
    -0.06
    ullo
    -0.06
    voj
    -0.06
    halb
    -0.06
    ixon
    -0.06
     Spin
    -0.06
    ellas
    -0.06
    lobs
    -0.06
    POSITIVE LOGITS
    597
    0.07
    _connector
    0.06
    532
    0.06
    939
    0.06
    Bindable
    0.06
    287
    0.06
    ENU
    0.06
     Kem
    0.06
     kem
    0.06
    ModelProperty
    0.06
    Activations Density 0.012%

    No Known Activations