© 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. 15-LLAMASCOPE-RES-131K
    6. 692
    Prev
    Next
    INDEX
    Explanations

    exclamatory or enthusiastic phrases about performances or shows

    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
    ELLOW
    -0.07
    edor
    -0.07
     polož
    -0.07
    Äĥr
    -0.07
    efe
    -0.07
    æ¼
    -0.07
    åĺ
    -0.07
    /*č↵
    -0.07
    pta
    -0.06
    inem
    -0.06
    POSITIVE LOGITS
    [s
    0.06
     Favor
    0.06
    aterno
    0.06
     Pickup
    0.06
    ActionButton
    0.06
     Gazette
    0.06
    .BorderFactory
    0.06
    è´¨éĩı
    0.05
    ãĥ¥ãĥ¼
    0.05
     [
    0.05
    Activations Density 0.014%

    No Known Activations