© 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. 94076
    Prev
    Next
    INDEX
    Explanations

    instances of numeric values or figures

    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
    chos
    -0.08
    hurst
    -0.08
     desc
    -0.07
    iker
    -0.07
    rid
    -0.06
     sor
    -0.06
    Äĥm
    -0.06
    urst
    -0.06
     wow
    -0.06
    ilden
    -0.06
    POSITIVE LOGITS
     Daly
    0.07
    st
    0.07
    /XMLSchema
    0.06
    ston
    0.06
     Denis
    0.06
     Derrick
    0.06
    gin
    0.06
    .structure
    0.06
    eger
    0.06
    oler
    0.06
    Activations Density 0.036%

    No Known Activations