© 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. 18005
    Prev
    Next
    INDEX
    Explanations

    instances of lack of communication or consultation

    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
    ãĤ¥
    -0.08
    егоÑĢ
    -0.08
    ãĥł
    -0.07
     IRequest
    -0.07
    rada
    -0.07
    posables
    -0.07
    chor
    -0.06
     spons
    -0.06
    人åı£
    -0.06
    mal
    -0.06
    POSITIVE LOGITS
     involvement
    0.11
     involved
    0.10
     participation
    0.09
     notification
    0.08
     consulted
    0.07
     notified
    0.07
     particip
    0.07
     share
    0.07
     Inv
    0.07
     involve
    0.07
    Activations Density 0.026%

    No Known Activations