© 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. 93564
    Prev
    Next
    INDEX
    Explanations

    genres and classifications related to film and television

    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
     Myers
    -0.06
    omb
    -0.06
    icensing
    -0.06
    rese
    -0.06
     fixation
    -0.06
    нÑĤ
    -0.06
    Mess
    -0.06
    cq
    -0.06
    ÅĦ
    -0.06
    StackTrace
    -0.05
    POSITIVE LOGITS
    linger
    0.08
    /goto
    0.07
    ëŀ
    0.07
     stru
    0.07
    âĹİ
    0.07
    IDL
    0.07
     opat
    0.07
     sami
    0.07
    etto
    0.07
     menn
    0.06
    Activations Density 0.001%

    No Known Activations