© 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. 15-LLAMASCOPE-RES-131K
    11. 90026
    Prev
    Next
    INDEX
    Explanations

    positive descriptors related to artistic execution and production quality

    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
    aginator
    -0.07
    że
    -0.06
     ])->
    -0.06
    agy
    -0.06
     Emanuel
    -0.06
     bystand
    -0.06
    unday
    -0.06
    typings
    -0.06
    .Compiler
    -0.06
     vic
    -0.05
    POSITIVE LOGITS
    DED
    0.07
    resse
    0.07
    ifice
    0.06
     executed
    0.06
    /exec
    0.06
    ignon
    0.06
     бÑĥдÑĤо
    0.06
    ypad
    0.06
    Ùİت
    0.06
    ayıp
    0.06
    Activations Density 0.024%

    No Known Activations