© 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 EvalsExportsinterp-engineNEWAPI 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. 15595
    Prev
    Next
    INDEX
    Explanations

    confrontational dialogue and statements about consequences

    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
    IOR
    -0.08
    nÄĽ
    -0.07
    icap
    -0.07
    곤
    -0.07
    ög
    -0.07
    _dtype
    -0.07
    SocketAddress
    -0.07
    viz
    -0.06
    ÅĻÃŃž
    -0.06
    å±
    -0.06
    POSITIVE LOGITS
     buzz
    0.06
    942
    0.06
     Blond
    0.06
    IOUS
    0.06
    enan
    0.05
    ZY
    0.05
     eyeb
    0.05
    _counters
    0.05
    355
    0.05
    099
    0.05
    Activations Density 0.039%

    No Known Activations