© 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. 119591
    Prev
    Next
    INDEX
    Explanations

    questions about murder and the investigation surrounding it

    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
    olah
    -0.07
    merce
    -0.07
    989
    -0.07
    isoner
    -0.07
    Ø¡
    -0.07
    placeholders
    -0.07
    avir
    -0.07
    .foundation
    -0.07
    itate
    -0.06
     ëĤĺìĺ¤
    -0.06
    POSITIVE LOGITS
     responsible
    0.09
    (s
    0.07
     someone
    0.07
     either
    0.07
     who
    0.07
     logical
    0.07
    uling
    0.06
     Logical
    0.06
    did
    0.06
     did
    0.06
    Activations Density 0.017%

    No Known Activations