© 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. 73298
    Prev
    Next
    INDEX
    Explanations

    references to clips and their modifications or attachments in a context involving equipment or tools

    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
    Tpl
    -0.08
    ask
    -0.07
    (=)
    -0.07
    tracted
    -0.07
    梯
    -0.07
    poss
    -0.07
    μη
    -0.07
    .sig
    -0.06
    _TP
    -0.06
     passe
    -0.06
    POSITIVE LOGITS
     again
    0.07
    pite
    0.06
     previous
    0.06
    raison
    0.06
    lier
    0.06
    romise
    0.06
    ifié
    0.06
     Patreon
    0.06
    ideographic
    0.06
    .googlecode
    0.06
    Activations Density 0.000%

    No Known Activations