© 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. 27859
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific person named Ed

    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
    ois
    -0.06
    /vnd
    -0.06
    lients
    -0.06
    _EXTERN
    -0.06
    orage
    -0.06
    ellan
    -0.06
    -minded
    -0.06
    eer
    -0.06
    /ts
    -0.06
    _exempt
    -0.06
    POSITIVE LOGITS
    s
    0.09
    sel
    0.09
    олÑĮно
    0.08
    scape
    0.08
    stein
    0.07
    itted
    0.07
    vard
    0.07
    QRST
    0.07
    asel
    0.07
    æ¸Ī
    0.07
    Activations Density 0.010%

    No Known Activations