© 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. 125354
    Prev
    Next
    INDEX
    Explanations

    references to groups of people and their reactions

    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
    çŃĭ
    -0.06
    osa
    -0.06
    .SIG
    -0.06
    Tomorrow
    -0.06
    ubi
    -0.06
    éĻIJ
    -0.06
     SIL
    -0.06
    .cgi
    -0.06
     squeez
    -0.05
    éģĩ
    -0.05
    POSITIVE LOGITS
     voyeur
    0.07
     curiosity
    0.07
     nearby
    0.07
    itzer
    0.06
    _COPY
    0.06
    forman
    0.06
     invasive
    0.06
    odash
    0.06
     curious
    0.06
    Nos
    0.06
    Activations Density 0.025%

    No Known Activations