© 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. 123764
    Prev
    Next
    INDEX
    Explanations

    mentions of public figures, particularly in relation to personal relationships or events

    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
    essen
    -0.07
    orama
    -0.07
    thro
    -0.07
    _media
    -0.07
    .LayoutStyle
    -0.07
    eÄį
    -0.06
    ÑĢеÑī
    -0.06
    xc
    -0.06
    cad
    -0.06
    ctxt
    -0.06
    POSITIVE LOGITS
    zym
    0.07
    axe
    0.07
    IGN
    0.06
    ignet
    0.06
     ET
    0.06
    ioni
    0.06
    dens
    0.06
    çĢ¬
    0.06
    KeyType
    0.06
    setUp
    0.06
    Activations Density 0.008%

    No Known Activations