© 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. 93268
    Prev
    Next
    INDEX
    Explanations

    phrases indicating quantity or frequency

    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
    endor
    -0.07
    μÏĢο
    -0.07
    ras
    -0.07
     Latest
    -0.07
    erval
    -0.07
    .tbl
    -0.06
    alore
    -0.06
     latest
    -0.06
    ghan
    -0.06
    ReuseIdentifier
    -0.06
    POSITIVE LOGITS
    548
    0.07
    iere
    0.06
    elli
    0.06
     tutar
    0.06
    Ìĥ
    0.06
    ito
    0.06
     sple
    0.06
    gger
    0.06
    elp
    0.06
    žen
    0.06
    Activations Density 0.024%

    No Known Activations