© 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. 30929
    Prev
    Next
    INDEX
    Explanations

    mentions of personal data and privacy concerns

    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
    ounder
    -0.07
    arna
    -0.07
    è¶
    -0.07
    arbon
    -0.07
    anou
    -0.06
    bern
    -0.06
    aln
    -0.06
    onta
    -0.06
    render
    -0.06
    inou
    -0.06
    POSITIVE LOGITS
    åĩī
    0.07
    engin
    0.06
    ihar
    0.06
    ered
    0.06
    ообÑĢаз
    0.06
     Dealer
    0.06
     Jury
    0.06
     داخÙĦ
    0.06
    ief
    0.05
    .dd
    0.05
    Activations Density 0.003%

    No Known Activations