© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 98893
    Prev
    Next
    INDEX
    Explanations

    code structure related to public methods in a programming context

    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
    urga
    -0.07
    zilla
    -0.06
    rape
    -0.06
     suck
    -0.06
    achment
    -0.06
    елÑĮ
    -0.06
    anka
    -0.06
    ulsion
    -0.06
    .googleapis
    -0.06
    869
    -0.06
    POSITIVE LOGITS
    ยว
    0.07
    è»
    0.07
    !=(
    0.06
    ÃĹ</
    0.06
    ').'
    0.06
    outu
    0.06
    ¶Ī
    0.06
    æĹıèĩªæ²»
    0.06
    ÏĥÏĦε
    0.06
    cret
    0.06
    Activations Density 0.002%

    No Known Activations