© 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. 95375
    Prev
    Next
    INDEX
    Explanations

    words related to negative or discouraging sentiments

    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
    hind
    -0.08
    erties
    -0.08
    ullet
    -0.08
    ionale
    -0.07
    VL
    -0.07
    oleÄį
    -0.07
    licted
    -0.07
    halt
    -0.07
    isContained
    -0.07
    bidden
    -0.07
    POSITIVE LOGITS
     dis
    0.13
    (dis
    0.10
    Dis
    0.08
    /dis
    0.08
    .dis
    0.08
     Dis
    0.08
    dis
    0.08
    -dis
    0.07
    .Dis
    0.07
     tr
    0.07
    Activations Density 0.014%

    No Known Activations