© 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. 28020
    Prev
    Next
    INDEX
    Explanations

    instances of the word "value" in various contexts

    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
     огÑĢа
    -0.10
     fetisch
    -0.09
    abox
    -0.09
    ãĢ
    -0.09
     имÑĥ
    -0.09
    ÃŃny
    -0.09
    rowable
    -0.09
    ãĢĤ↵↵↵↵↵↵
    -0.08
     еÑģÑĤе
    -0.08
    nodoc
    -0.08
    POSITIVE LOGITS
    /or
    0.07
    Âł
    0.07
    0.07
     /
    0.06
    ,
    0.06
    ;
    0.06
    avad
    0.06
    [
    0.06
    /
    0.06
    712
    0.06
    Activations Density 0.013%

    No Known Activations