© 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. 73543
    Prev
    Next
    INDEX
    Explanations

    references to political situations and behaviors

    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
    #ac
    -0.07
    PHA
    -0.07
    enson
    -0.07
    âĢ¢↵↵
    -0.06
     JMP
    -0.06
    елÑĮзÑı
    -0.06
    UCT
    -0.06
    imate
    -0.06
    elia
    -0.06
    ighton
    -0.06
    POSITIVE LOGITS
    atÃŃm
    0.07
    Äįel
    0.06
     slu
    0.06
     mav
    0.06
    ouple
    0.06
    ç©´
    0.06
    .fhir
    0.06
     transcript
    0.06
    ,,
    0.06
    axon
    0.06
    Activations Density 0.001%

    No Known Activations