© 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. 15-LLAMASCOPE-RES-131K
    11. 86256
    Prev
    Next
    INDEX
    Explanations

    contractual terms and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    A period marking the end of a complete sentence or paragraph, often in technical or explanatory content, sometimes followed by a paragraph break.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    cca
    -0.09
     Hlav
    -0.07
    'gc
    -0.07
    /Dk
    -0.07
    ucc
    -0.07
     (č↵
    -0.07
    igr
    -0.07
    STALL
    -0.06
    umo
    -0.06
     lai
    -0.06
    POSITIVE LOGITS
     then
    0.11
    then
    0.09
     Then
    0.08
    Then
    0.08
    thouse
    0.08
     next
    0.08
     THEN
    0.07
     Next
    0.07
     bip
    0.07
     when
    0.07
    Activations Density 0.039%

    No Known Activations