© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 39144
    Prev
    Next
    INDEX
    Explanations

    references to product collections and seasonal themes

    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
     Morrow
    -0.07
     Ney
    -0.07
     Bookmark
    -0.06
    eah
    -0.06
     diss
    -0.06
     frequ
    -0.06
    ÃŃas
    -0.05
     th
    -0.05
     Pai
    -0.05
    ạch
    -0.05
    POSITIVE LOGITS
    uzz
    0.07
    itta
    0.07
    .MONTH
    0.07
    iore
    0.07
    iko
    0.07
    orio
    0.07
    adius
    0.07
    .loaded
    0.07
    iny
    0.07
     jedn
    0.07
    Activations Density 0.001%

    No Known Activations