© 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. 104181
    Prev
    Next
    INDEX
    Explanations

    mentions of physical or metaphorical strength and its various forms

    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
    ation
    -0.07
    vip
    -0.07
    latin
    -0.07
    layan
    -0.07
    ê
    -0.07
    arat
    -0.06
    ack
    -0.06
    à¤ķरण
    -0.06
    istani
    -0.06
    ponder
    -0.06
    POSITIVE LOGITS
    holds
    0.11
    bow
    0.09
    /power
    0.09
    -strong
    0.09
    /we
    0.08
     Weak
    0.08
     weakness
    0.08
    bucks
    0.07
     weak
    0.07
    weak
    0.07
    Activations Density 0.016%

    No Known Activations