© 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. 15-LLAMASCOPE-RES-131K
    11. 86736
    Prev
    Next
    INDEX
    Explanations

    programming or coding language frameworks and libraries

    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
    unga
    -0.08
    olvable
    -0.07
    ainless
    -0.07
    urm
    -0.07
    lein
    -0.07
    umbo
    -0.07
    ossal
    -0.07
    ewire
    -0.07
    mue
    -0.07
    mdir
    -0.07
    POSITIVE LOGITS
    SSF
    0.06
     Blo
    0.06
     blo
    0.06
    blo
    0.06
    UGH
    0.06
    icorn
    0.06
    ogn
    0.06
    mitt
    0.05
     mailbox
    0.05
     Wake
    0.05
    Activations Density 0.007%

    No Known Activations