© 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. 84037
    Prev
    Next
    INDEX
    Explanations

    references to personal or familial relationships and support

    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
    erras
    -0.08
    elon
    -0.07
    isque
    -0.07
    kits
    -0.07
    okit
    -0.07
    tement
    -0.07
    eload
    -0.06
    ritz
    -0.06
    endor
    -0.06
    quis
    -0.06
    POSITIVE LOGITS
     authorities
    0.09
    DAL
    0.07
     submitting
    0.07
    á»ijc
    0.07
     submit
    0.06
     employers
    0.06
    RLF
    0.06
     Congress
    0.06
     regulators
    0.06
     Authorities
    0.06
    Activations Density 0.085%

    No Known Activations