© 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. 29490
    Prev
    Next
    INDEX
    Explanations

    themes related to inner struggles and psychological challenges

    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
    ascript
    -0.06
    å½ķ
    -0.06
     Skull
    -0.06
    erview
    -0.06
     adulti
    -0.06
    avig
    -0.06
     omnip
    -0.06
    ophe
    -0.06
     grat
    -0.06
    ivar
    -0.06
    POSITIVE LOGITS
     Miche
    0.06
    meric
    0.06
     America
    0.06
     motif
    0.06
    America
    0.06
    .nih
    0.06
     indigenous
    0.06
    htags
    0.06
     Wend
    0.06
     proper
    0.06
    Activations Density 0.002%

    No Known Activations