© 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. 17-LLAMASCOPE-RES-131K
    11. 75241
    Prev
    Next
    INDEX
    Explanations

    expressions of affection or positive sentiment

    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
    ieux
    -0.06
     Meh
    -0.06
    ahan
    -0.06
     myself
    -0.06
    Ｉ
    -0.06
    arta
    -0.06
     creampie
    -0.06
    elize
    -0.06
    .FieldName
    -0.06
    жÑĥ
    -0.06
    POSITIVE LOGITS
    ograd
    0.08
    ailable
    0.07
    ably
    0.07
    /use
    0.07
     this
    0.07
     Caldwell
    0.06
    aira
    0.06
    abus
    0.06
    eland
    0.06
    benh
    0.06
    Activations Density 0.011%

    No Known Activations