© 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. 27241
    Prev
    Next
    INDEX
    Explanations

    recommendations and requirements related to visa applications and related processes

    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
    cust
    -0.06
    otas
    -0.06
    epad
    -0.06
    aset
    -0.06
     Nullable
    -0.06
    ope
    -0.06
    airo
    -0.06
    umba
    -0.06
    ennie
    -0.06
    uento
    -0.06
    POSITIVE LOGITS
    UBLE
    0.08
     familiar
    0.07
    implify
    0.07
    ãģĹãĤĩ
    0.07
    pleted
    0.06
    847
    0.06
     Fam
    0.06
    plete
    0.06
    uese
    0.06
     accurate
    0.06
    Activations Density 0.026%

    No Known Activations