© 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. 72324
    Prev
    Next
    INDEX
    Explanations

    instances of guidance or solutions in technical discussions

    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
     ÐĴики
    -0.08
    uyo
    -0.08
     otherwise
    -0.07
    (æľĪ
    -0.07
    asu
    -0.07
    viously
    -0.06
    antlr
    -0.06
    سÙĪب
    -0.06
    ardless
    -0.06
     OTHERWISE
    -0.06
    POSITIVE LOGITS
    ambi
    0.07
     informations
    0.06
    “
    0.06
    ạm
    0.06
    ega
    0.06
    pline
    0.06
     zun
    0.06
    rl
    0.05
    hm
    0.05
    (ur
    0.05
    Activations Density 0.020%

    No Known Activations