© 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. 42483
    Prev
    Next
    INDEX
    Explanations

    descriptions of difficulty or challenges

    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
    quia
    -0.07
    gency
    -0.07
    GENCY
    -0.07
    mony
    -0.07
    emain
    -0.07
    sov
    -0.07
    donnees
    -0.07
    gence
    -0.06
     preco
    -0.06
    oose
    -0.06
    POSITIVE LOGITS
     khÄĥn
    0.08
    ening
    0.07
    hard
    0.07
    -hard
    0.07
    uster
    0.07
    ened
    0.07
    wig
    0.06
    478
    0.06
    marsh
    0.06
    bie
    0.06
    Activations Density 0.015%

    No Known Activations