© 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. 86459
    Prev
    Next
    INDEX
    Explanations

    instances of distancing or disavowing actions or statements

    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
     Zus
    -0.07
    νÏĮ
    -0.07
     atmospheric
    -0.07
    altern
    -0.07
    ija
    -0.07
    ARTH
    -0.07
    newInstance
    -0.06
    alez
    -0.06
    ebek
    -0.06
     Petit
    -0.06
    POSITIVE LOGITS
     distance
    0.09
     Distance
    0.09
     distancing
    0.09
     association
    0.08
     dissoci
    0.08
    distance
    0.08
    è·ĿéĽ¢
    0.08
     distances
    0.07
     ownership
    0.07
     embarrassment
    0.07
    Activations Density 0.020%

    No Known Activations