© 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. 62996
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate subordinate conditions or clauses

    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
     неÑĢ
    -0.09
    ìĤ
    -0.08
    ãĥ¼ãĥ¬
    -0.07
    rá
    -0.07
    .native
    -0.07
    ÑĢÑĥб
    -0.07
    /DTD
    -0.07
    nts
    -0.07
    CHASE
    -0.07
    raquo
    -0.07
    POSITIVE LOGITS
     conditions
    0.09
     under
    0.09
     guidance
    0.08
    est
    0.08
     ausp
    0.08
     cover
    0.07
     pseud
    0.07
     circumstances
    0.07
     plan
    0.06
     threat
    0.06
    Activations Density 0.019%

    No Known Activations