© 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. 119889
    Prev
    Next
    INDEX
    Explanations

    action verbs indicating progress or movement

    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
    ص
    -0.07
    elda
    -0.06
    403
    -0.06
     forg
    -0.05
     дов
    -0.05
    _serialize
    -0.05
    ishlist
    -0.05
    forum
    -0.05
    371
    -0.05
    373
    -0.05
    POSITIVE LOGITS
    plib
    0.08
    SCO
    0.08
    uber
    0.07
    egg
    0.07
    oeff
    0.07
    ädchen
    0.07
     Vest
    0.07
    à¥ľà¤ķ
    0.06
    ussen
    0.06
    alking
    0.06
    Activations Density 0.000%

    No Known Activations