© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 61312
    Prev
    Next
    INDEX
    Explanations

    interactions involving mental health and support sessions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text describing professional meetings, interviews, or consultations, including their settings, formats, durations, and participants.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     Dorm
    -0.09
     dorm
    -0.07
    itic
    -0.07
    flen
    -0.06
     Tem
    -0.06
    cona
    -0.06
    ovat
    -0.06
    etic
    -0.06
    adir
    -0.06
    mán
    -0.06
    POSITIVE LOGITS
     interview
    0.10
    Interview
    0.09
    erview
    0.09
    _sess
    0.09
     entrev
    0.09
     Interview
    0.09
    =session
    0.09
     appointments
    0.08
     interviews
    0.08
    -session
    0.08
    Activations Density 0.072%

    No Known Activations