© 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. 18505
    Prev
    Next
    INDEX
    Explanations

    instances of "were" along with phrases indicating potential outcomes or hypothetical situations

    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
    à¸ģ
    -0.08
    ses
    -0.08
    sel
    -0.07
    dale
    -0.07
    room
    -0.07
    ãģĦãĤĭ
    -0.07
    ser
    -0.07
    ru
    -0.07
    son
    -0.07
    /off
    -0.07
    POSITIVE LOGITS
    pose
    0.07
    lessly
    0.07
    roj
    0.07
    ãģ¹ãģį
    0.07
    entimes
    0.07
    å·±
    0.07
     to
    0.07
    odelist
    0.07
    YLES
    0.07
    INUX
    0.07
    Activations Density 0.019%

    No Known Activations