© 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. 126230
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional support and advice

    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
    thon
    -0.07
    æĭ³
    -0.07
    uci
    -0.07
    óm
    -0.07
    èµ
    -0.07
    UNUSED
    -0.07
    rouch
    -0.06
    arget
    -0.06
    idential
    -0.06
    .cloudflare
    -0.06
    POSITIVE LOGITS
     busy
    0.06
     replied
    0.06
     schedule
    0.06
    estatus
    0.05
     Busy
    0.05
    Reply
    0.05
    IME
    0.05
     dat
    0.05
    GH
    0.05
    LTR
    0.05
    Activations Density 0.002%

    No Known Activations