© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 119065
    Prev
    Next
    INDEX
    Explanations

    terms related to health complications and their impacts

    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
     iken
    -0.08
    ERSHEY
    -0.07
    iras
    -0.07
    cntl
    -0.07
    jem
    -0.07
     srd
    -0.07
     Karlov
    -0.07
    ipur
    -0.07
    ÅĻ
    -0.07
    arness
    -0.07
    POSITIVE LOGITS
     confidence
    0.08
     available
    0.08
    HC
    0.07
     quality
    0.07
     morale
    0.06
     trust
    0.06
     Available
    0.06
    Available
    0.06
     effective
    0.06
     motivation
    0.06
    Activations Density 0.064%

    No Known Activations