Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4645
    Prev
    Next
    INDEX
    Explanations

    words related to chemical compounds

    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
    827
    -0.08
    ì§ĵ
    -0.08
    837
    -0.07
    istar
    -0.06
    ulta
    -0.06
    237
    -0.06
    illard
    -0.06
    inya
    -0.06
    _FACE
    -0.06
    887
    -0.05
    POSITIVE LOGITS
    ates
    0.10
    ATES
    0.08
    ate
    0.08
     plastic
    0.08
    CEEDED
    0.07
     Plastic
    0.07
    thal
    0.07
    lates
    0.07
    prene
    0.07
    .nlm
    0.07
    Activations Density 0.001%

    No Known Activations