© 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. 98246
    Prev
    Next
    INDEX
    Explanations

    mentions of additional information or actions related to content

    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
     h
    -0.08
    *
    -0.07
     "
    -0.07
     *
    -0.07
    -
    -0.07
    _
    -0.06
    ,
    -0.06
    Âł
    -0.06
     ar
    -0.06
    ;
    -0.06
    POSITIVE LOGITS
    $core
    0.10
    .scalablytyped
    0.09
    #
    0.09
    Äįel
    0.09
    getAs
    0.09
    ervas
    0.09
    .ribbon
    0.09
    аÑĢод
    0.09
    _ctor
    0.09
    LLU
    0.09
    Activations Density 0.008%

    No Known Activations