© 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. 93881
    Prev
    Next
    INDEX
    Explanations

    phrases indicating permissions and access rights

    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
    ileo
    -0.06
     yours
    -0.06
    builtin
    -0.06
    umin
    -0.06
    ulen
    -0.06
    upil
    -0.06
    284
    -0.06
    apse
    -0.06
    ernals
    -0.06
    asia
    -0.06
    POSITIVE LOGITS
    FIT
    0.07
     Arlington
    0.07
    FUNC
    0.07
     æ´
    0.07
    -ie
    0.07
    azar
    0.06
    ีว
    0.06
    ãĤ¼
    0.06
    _cleanup
    0.06
    .ribbon
    0.06
    Activations Density 0.001%

    No Known Activations