© 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. 17-LLAMASCOPE-RES-131K
    11. 126107
    Prev
    Next
    INDEX
    Explanations

    references to therapeutic techniques and approaches in psychology

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

    Text describing therapeutic approaches, counseling methodologies, and the therapist-client relationship.

    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
     pre
    -0.06
     deg
    -0.06
    ivi
    -0.06
    /cmd
    -0.06
    alloca
    -0.06
    atty
    -0.06
     careers
    -0.06
    kker
    -0.06
     forecast
    -0.06
    ertz
    -0.06
    POSITIVE LOGITS
    Rate
    0.07
    alker
    0.07
     mListener
    0.07
     Confidential
    0.07
    LOPT
    0.07
     getClient
    0.07
    Clients
    0.07
    à¥Ĥरत
    0.06
    è¿ħ
    0.06
    inspace
    0.06
    Activations Density 0.006%

    No Known Activations