Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 128787
    Prev
    Next
    INDEX
    Explanations

    references to various social groups and identities

    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
     δε
    -0.07
    ANTE
    -0.07
    gabe
    -0.07
    ädchen
    -0.07
    uela
    -0.06
    MN
    -0.06
    .scalablytyped
    -0.06
    afen
    -0.06
    ="__
    -0.06
    auss
    -0.06
    POSITIVE LOGITS
     whose
    0.13
     who
    0.12
    whose
    0.10
    who
    0.09
     коÑĤ
    0.07
    apan
    0.07
     trying
    0.07
     incom
    0.06
    ipple
    0.06
     koji
    0.06
    Activations Density 0.051%

    No Known Activations