© 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. 16307
    Prev
    Next
    INDEX
    Explanations

    instructions for adding ingredients or components in a cooking context

    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
    ëį°
    -0.08
    enders
    -0.08
    phem
    -0.08
     doma
    -0.07
    alse
    -0.07
    ienia
    -0.07
    оло
    -0.07
    ksen
    -0.07
    foon
    -0.07
    ãĥ¬ãĥ³
    -0.06
    POSITIVE LOGITS
    iton
    0.06
    asley
    0.06
    /upload
    0.06
    /Set
    0.06
    anel
    0.06
     fray
    0.06
     the
    0.06
     Ont
    0.05
    ingham
    0.05
    sdale
    0.05
    Activations Density 0.018%

    No Known Activations