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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 40191
    Prev
    Next
    INDEX
    Explanations

    references to surveillance and invasion of privacy

    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
    _$_
    -0.08
    ê´
    -0.07
    _interrupt
    -0.07
    icos
    -0.07
    лини
    -0.07
    ênh
    -0.07
    enza
    -0.07
    ropp
    -0.07
    VarChar
    -0.07
    æ¦ľ
    -0.07
    POSITIVE LOGITS
     intimate
    0.07
     frequ
    0.07
     Mov
    0.07
     Kons
    0.07
     movements
    0.06
     religious
    0.06
    vas
    0.06
    afs
    0.06
     patterns
    0.06
    ow
    0.06
    Activations Density 0.008%

    No Known Activations