© 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. 17-LLAMASCOPE-RES-131K
    11. 31435
    Prev
    Next
    INDEX
    Explanations

    information related to advantages and disadvantages in systems or classifications

    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
     pitch
    -0.07
    aison
    -0.07
    tright
    -0.07
    ÄŁÃ¼
    -0.06
    /boot
    -0.06
    nof
    -0.06
     Kız
    -0.06
     æ
    -0.06
    άÏĥ
    -0.06
    epar
    -0.06
    POSITIVE LOGITS
     slightly
    0.11
     intermediate
    0.10
     medium
    0.09
    medium
    0.09
     moderately
    0.09
     slight
    0.08
    -middle
    0.08
    Still
    0.08
     middle
    0.08
     Still
    0.08
    Activations Density 0.041%

    No Known Activations