© 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. 15-LLAMASCOPE-RES-131K
    11. 87336
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals involved in political controversies, particularly from the FBI

    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
    ointment
    -0.07
    ippers
    -0.06
    ikipedia
    -0.06
     McCartney
    -0.06
    ointments
    -0.06
    PARATOR
    -0.06
    UFF
    -0.06
    LF
    -0.06
    ож
    -0.06
    rooms
    -0.06
    POSITIVE LOGITS
    linkplain
    0.07
    zeug
    0.07
    áng
    0.07
     Karma
    0.07
    .gov
    0.06
    olini
    0.06
    %c
    0.06
    Slf
    0.06
     whims
    0.06
    lectron
    0.06
    Activations Density 0.002%

    No Known Activations