© 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. 108643
    Prev
    Next
    INDEX
    Explanations

    expressions of sharing or collaboration

    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
    Ì
    -0.09
    ̣
    -0.07
    ell
    -0.07
    itta
    -0.06
    dn
    -0.06
    165
    -0.06
    ium
    -0.06
    iy
    -0.06
    ir
    -0.06
    DN
    -0.06
    POSITIVE LOGITS
     us
    0.09
    .Guna
    0.08
     nhau
    0.08
     audiences
    0.07
     wider
    0.07
     strt
    0.07
    ebi
    0.07
     Screw
    0.07
     ÑģÑĥдÑĥ
    0.07
    inaire
    0.06
    Activations Density 0.008%

    No Known Activations