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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 56728
    Prev
    Next
    INDEX
    Explanations

    words related to identity and social issues

    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
     bonds
    -0.07
    ĶåĽŀ
    -0.07
     bond
    -0.06
    ülen
    -0.06
    ahir
    -0.06
     bour
    -0.06
    rimp
    -0.06
    483
    -0.06
     contents
    -0.06
    zÅij
    -0.06
    POSITIVE LOGITS
    yonel
    0.07
     ga
    0.07
    $MESS
    0.07
    engin
    0.07
    βο
    0.07
    ffd
    0.07
    roz
    0.06
    $LANG
    0.06
    AtA
    0.06
    hte
    0.06
    Activations Density 0.003%

    No Known Activations