© 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. 17559
    Prev
    Next
    INDEX
    Explanations

    references to women's rights and historical achievements related to names and identity

    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
    uw
    -0.07
    ipar
    -0.07
    bole
    -0.07
    .AddDays
    -0.07
    ipur
    -0.07
    ENOMEM
    -0.07
    añ
    -0.07
    oute
    -0.07
    _userdata
    -0.07
     spin
    -0.07
    POSITIVE LOGITS
     surname
    0.15
    å§ĵ
    0.13
     name
    0.13
     names
    0.11
    surname
    0.11
    å§ĵåIJį
    0.10
    .name
    0.10
    name
    0.10
    .surname
    0.10
    -name
    0.09
    Activations Density 0.093%

    No Known Activations