© 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. 4922
    Prev
    Next
    INDEX
    Explanations

    elements of problematic interpersonal communication and handling situations involving negative interactions

    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
    indow
    -0.08
    chyb
    -0.07
    luet
    -0.07
     tô
    -0.07
    amak
    -0.07
    artner
    -0.07
    ecast
    -0.06
    ¯ÃĤ
    -0.06
    omid
    -0.06
    ras
    -0.06
    POSITIVE LOGITS
     again
    0.45
    again
    0.40
     Again
    0.36
    Again
    0.35
     AGAIN
    0.28
     novamente
    0.27
     wieder
    0.25
    AGAIN
    0.25
    _again
    0.25
     Ñģнова
    0.23
    Activations Density 0.235%

    No Known Activations