© 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. 124550
    Prev
    Next
    INDEX
    Explanations

    programming function declarations and structure

    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
    chia
    -0.06
     @$_
    -0.06
    AndGet
    -0.06
     var
    -0.06
    CHK
    -0.06
     vars
    -0.06
     Spor
    -0.06
     VARIANT
    -0.06
    ARA
    -0.06
     Ä°z
    -0.05
    POSITIVE LOGITS
    icator
    0.07
    tae
    0.06
     Wit
    0.06
    #ae
    0.06
    cade
    0.06
    ehen
    0.06
    ×ķ
    0.06
    ails
    0.06
    yla
    0.06
    ereo
    0.06
    Activations Density 0.006%

    No Known Activations