© 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. 80942
    Prev
    Next
    INDEX
    Explanations

    words indicating evaluation or summary

    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
    enza
    -0.06
    неÑĢ
    -0.06
    اض
    -0.06
    _deinit
    -0.06
     dÄ±ÅŁÄ±nda
    -0.06
     Polly
    -0.06
     vyh
    -0.06
    _REUSE
    -0.06
    .='
    -0.06
    .libs
    -0.06
    POSITIVE LOGITS
     Ced
    0.07
    igu
    0.07
    ĥn
    0.06
    ajan
    0.06
    asaki
    0.06
    licted
    0.06
    ecz
    0.06
    orny
    0.06
    üç
    0.06
    icone
    0.06
    Activations Density 0.026%

    No Known Activations