© 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 EvalsExportsAPI 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. 78358
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize personal responsibility or important tasks

    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
    _subtype
    -0.07
    ainment
    -0.07
    kar
    -0.07
    ิà¹ī
    -0.06
    Expiration
    -0.06
     ÅŁÃ¼ph
    -0.06
    .AI
    -0.06
    bitset
    -0.06
    ă
    -0.06
    msgs
    -0.06
    POSITIVE LOGITS
    osoph
    0.06
    sted
    0.06
    mith
    0.06
    osti
    0.06
    omens
    0.06
    Ä°Y
    0.06
    ipse
    0.06
    oci
    0.06
    aux
    0.06
    gmail
    0.06
    Activations Density 0.000%

    No Known Activations