© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 17414
    Prev
    Next
    INDEX
    Explanations

    determinative words that indicate totality or completeness

    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
    entions
    -0.06
    itution
    -0.06
    ascus
    -0.06
     any
    -0.06
    ocard
    -0.06
    ì¹´ëĿ¼
    -0.06
    дина
    -0.06
    zÅij
    -0.06
     Kerr
    -0.06
     otherwise
    -0.06
    POSITIVE LOGITS
    ong
    0.08
     uv
    0.07
    uv
    0.07
    orch
    0.07
    u
    0.07
    ONG
    0.07
    ef
    0.06
    UV
    0.06
    tim
    0.06
    ãĥĭãĤ¢
    0.06
    Activations Density 0.004%

    No Known Activations