© 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. 3902
    Prev
    Next
    INDEX
    Explanations

    indicators of crime scene evidence

    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
    repid
    -0.06
    crate
    -0.06
    esson
    -0.06
     smo
    -0.06
    asset
    -0.06
     strapped
    -0.06
    à¹ĩà¸Ļà¸ŀ
    -0.06
    ships
    -0.06
     ahead
    -0.06
    thren
    -0.06
    POSITIVE LOGITS
    éı
    0.07
     evidence
    0.07
     traces
    0.07
    onse
    0.07
     found
    0.07
    عاÙĨ
    0.07
    æĿĤ
    0.07
    erras
    0.06
    ctrine
    0.06
    _RESERVED
    0.06
    Activations Density 0.009%

    No Known Activations