© 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. 72433
    Prev
    Next
    INDEX
    Explanations

    forms of the word "base" and its derivatives, as well as related concepts

    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
     Thi
    -0.06
     somebody
    -0.06
    ikk
    -0.06
    usher
    -0.06
    usch
    -0.06
     Lal
    -0.06
     Preston
    -0.06
    ingle
    -0.05
     manner
    -0.05
    /from
    -0.05
    POSITIVE LOGITS
    íķŃ
    0.07
    наÑĩе
    0.07
    ONO
    0.07
    .nano
    0.07
    iless
    0.07
    haar
    0.07
     yönetimi
    0.07
    emean
    0.07
    .openConnection
    0.07
    InRange
    0.07
    Activations Density 0.034%

    No Known Activations