© 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. 15-LLAMASCOPE-RES-131K
    11. 88572
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and jurisdictions

    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
    ingo
    -0.07
    ond
    -0.06
    inda
    -0.06
    loub
    -0.06
    flip
    -0.06
    upa
    -0.06
    nid
    -0.06
     flip
    -0.06
     scaleX
    -0.06
    lemn
    -0.06
    POSITIVE LOGITS
     where
    0.08
    venue
    0.07
    лÑİÑĩ
    0.07
    //{{
    0.07
    venues
    0.07
    ovice
    0.07
     à¤ľà¤¹
    0.07
    /count
    0.07
    .where
    0.06
    (where
    0.06
    Activations Density 0.007%

    No Known Activations