© 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. 106266
    Prev
    Next
    INDEX
    Explanations

    phrases that express suggestions or improvement related to processes and conditions

    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
    vÃŃc
    -0.07
    tÄĽÅ¾
    -0.07
    atee
    -0.07
    bies
    -0.07
    _fu
    -0.07
    gnore
    -0.07
    (æĹ¥
    -0.07
     prostitu
    -0.07
    lio
    -0.07
    semicolon
    -0.07
    POSITIVE LOGITS
    ingly
    0.10
    etheless
    0.10
    uably
    0.08
     kidding
    0.08
    umably
    0.08
    beit
    0.07
    pecially
    0.07
    icularly
    0.07
    ally
    0.07
    arily
    0.07
    Activations Density 0.407%

    No Known Activations