© 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. 98106
    Prev
    Next
    INDEX
    Explanations

    programming class definitions and structure in code

    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
    abbo
    -0.08
    afia
    -0.06
    fv
    -0.06
    еÑĩно
    -0.06
    OX
    -0.06
    reste
    -0.06
    attering
    -0.06
     pä
    -0.06
    zung
    -0.06
    ÑģоÑĤ
    -0.06
    POSITIVE LOGITS
    tor
    0.07
    acz
    0.07
    UGIN
    0.06
     lou
    0.06
    çĻĤ
    0.06
    posix
    0.06
    chyb
    0.06
    acons
    0.06
    ãģIJ
    0.06
    _TYPED
    0.06
    Activations Density 0.000%

    No Known Activations