© 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. 9-LLAMASCOPE-RES-131K
    11. 98555
    Prev
    Next
    INDEX
    Explanations

    terms related to media, films, and television productions

    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
     Gil
    -0.07
    209
    -0.07
    -0.07
     pie
    -0.07
     far
    -0.07
     Pie
    -0.06
     r
    -0.06
    ,
    -0.06
     d
    -0.06
     not
    -0.06
    POSITIVE LOGITS
     semiclass
    0.08
    icode
    0.08
    TickCount
    0.08
    etimes
    0.08
    ocrat
    0.08
    .cg
    0.08
    imbus
    0.08
     aime
    0.08
    abei
    0.08
    erap
    0.07
    Activations Density 0.022%

    No Known Activations