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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 61065
    Prev
    Next
    INDEX
    Explanations

    references to legal evidence and court rulings

    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
     Gib
    -0.07
    нен
    -0.06
    unately
    -0.06
    _hint
    -0.06
    $MESS
    -0.06
     ür
    -0.06
    ãģĭãģij
    -0.06
    بع
    -0.06
    uggy
    -0.06
    amient
    -0.06
    POSITIVE LOGITS
     nor
    0.10
     Nor
    0.09
     neither
    0.09
    Nor
    0.07
     therefore
    0.07
    oog
    0.07
     falls
    0.06
    acher
    0.06
     absence
    0.06
     cannot
    0.06
    Activations Density 0.065%

    No Known Activations