© 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. 86919
    Prev
    Next
    INDEX
    Explanations

    terms related to mental health issues and conditions

    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
    uliar
    -0.07
    emen
    -0.07
    morph
    -0.06
    ĨĴ
    -0.06
    971
    -0.06
    ctp
    -0.06
    WithValue
    -0.06
    din
    -0.06
    ISTRIBUT
    -0.06
    _DYNAMIC
    -0.06
    POSITIVE LOGITS
    utton
    0.08
    ebi
    0.06
     grav
    0.06
    ris
    0.06
    ãĥ¼ãĥ«ãĥī
    0.06
     Crowley
    0.06
     especially
    0.06
    UTTON
    0.06
     health
    0.05
    aux
    0.05
    Activations Density 0.006%

    No Known Activations