© 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. 107368
    Prev
    Next
    INDEX
    Explanations

    references to the role and influence of different entities or phenomena in various contexts

    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
    weit
    -0.08
    fty
    -0.08
    otti
    -0.07
    chwitz
    -0.07
    oram
    -0.07
    reachable
    -0.07
    NSS
    -0.07
    ezi
    -0.07
    estate
    -0.07
    icer
    -0.07
    POSITIVE LOGITS
     role
    0.08
     played
    0.07
    role
    0.07
    played
    0.07
     factor
    0.07
     intermedi
    0.07
    (role
    0.07
     religion
    0.07
    omb
    0.07
     Factor
    0.06
    Activations Density 0.017%

    No Known Activations