© 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. 93187
    Prev
    Next
    INDEX
    Explanations

    references to academic journal articles and their publishing details

    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
    ano
    -0.07
     Diversity
    -0.06
     col
    -0.06
     Col
    -0.06
     underlying
    -0.06
     Uncategorized
    -0.06
    igon
    -0.06
    ~
    -0.06
    arias
    -0.05
     ren
    -0.05
    POSITIVE LOGITS
    kke
    0.09
    ÄĻż
    0.08
     fishes
    0.07
    CTYPE
    0.07
    .abstract
    0.07
    ekk
    0.07
    apers
    0.07
    ipar
    0.07
    .Assign
    0.07
    ouz
    0.07
    Activations Density 0.003%

    No Known Activations