© 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. 9-LLAMASCOPE-RES-131K
    11. 94512
    Prev
    Next
    INDEX
    Explanations

    HTML attributes related to alignment and centering

    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
    Äħ
    -0.06
    ån
    -0.06
     Priv
    -0.06
     inv
    -0.06
     wen
    -0.05
     pleasure
    -0.05
     Hol
    -0.05
     Gir
    -0.05
    entially
    -0.05
     against
    -0.05
    POSITIVE LOGITS
    cela
    0.08
    etim
    0.07
    enal
    0.07
    yal
    0.07
    urvey
    0.07
    inho
    0.07
    VRT
    0.06
    spender
    0.06
    á»ĭp
    0.06
    kad
    0.06
    Activations Density 0.002%

    No Known Activations