© 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. 118888
    Prev
    Next
    INDEX
    Explanations

    commands and requests expressed with "let."

    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
    ogle
    -0.06
    WAY
    -0.06
    oodle
    -0.06
    оке
    -0.06
    ULA
    -0.06
    gu
    -0.06
    룬
    -0.06
    ikat
    -0.06
    maz
    -0.06
    bla
    -0.06
    POSITIVE LOGITS
    ting
    0.08
    upal
    0.07
    моÑĤ
    0.07
    ÙĬÙĨÙĬ
    0.07
    uples
    0.07
    é¨
    0.07
    zte
    0.06
    illard
    0.06
    viar
    0.06
    ÅŁa
    0.06
    Activations Density 0.016%

    No Known Activations