© 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. 27312
    Prev
    Next
    INDEX
    Explanations

    phrases indicating advice or recommendations about activities that should be avoided

    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
    ionic
    -0.07
    rav
    -0.07
    oux
    -0.06
    erra
    -0.06
    eps
    -0.06
    ãģİ
    -0.06
    zew
    -0.06
    zone
    -0.06
    verted
    -0.06
    chi
    -0.06
    POSITIVE LOGITS
    ucch
    0.07
    emoc
    0.07
     Banc
    0.07
    ëĵł
    0.07
    asl
    0.06
    asics
    0.06
    вай
    0.06
    .require
    0.06
    ëĭī
    0.06
    arrings
    0.06
    Activations Density 0.017%

    No Known Activations