© 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. 15-LLAMASCOPE-RES-131K
    11. 90102
    Prev
    Next
    INDEX
    Explanations

    marks related to measurement or specification of dimensions

    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
    ulen
    -0.07
    ÅĪ
    -0.07
    .ci
    -0.07
    Stars
    -0.06
    /feed
    -0.06
    EDIA
    -0.06
    æłª
    -0.06
    ffc
    -0.06
    .jetbrains
    -0.06
     VÅ¡ech
    -0.06
    POSITIVE LOGITS
    tras
    0.06
    /in
    0.06
    eters
    0.06
    endale
    0.06
    anes
    0.06
    dash
    0.06
    /from
    0.06
    ï¸ı
    0.06
    ettel
    0.06
    /of
    0.06
    Activations Density 0.007%

    No Known Activations