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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 119417
    Prev
    Next
    INDEX
    Explanations

    terms related to therapeutic practices and programs

    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
    é¨İ
    -0.06
     Hyp
    -0.06
    _insn
    -0.06
     obligation
    -0.06
    996
    -0.06
     Merchant
    -0.06
     mens
    -0.06
     оÑĩ
    -0.06
     merchant
    -0.06
    anta
    -0.06
    POSITIVE LOGITS
     therapeutic
    0.08
    essions
    0.07
    à¸Ĭร
    0.07
     Rounds
    0.07
    ifax
    0.07
    folios
    0.07
    åĪĽ
    0.07
    .paths
    0.07
    Sessions
    0.07
    ::::::::::::::::::::::::::::::::
    0.07
    Activations Density 0.011%

    No Known Activations