© 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. 87660
    Prev
    Next
    INDEX
    Explanations

    references to generational identities and characteristics

    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
    imest
    -0.07
    ugi
    -0.07
    -UA
    -0.07
    ias
    -0.07
    ance
    -0.06
    ucket
    -0.06
    obb
    -0.06
    วà¸Ļ
    -0.06
    ascimento
    -0.06
    deaux
    -0.06
    POSITIVE LOGITS
     Generation
    0.22
    Generation
    0.19
     generation
    0.19
    generation
    0.17
    _generation
    0.15
    -generation
    0.15
     покол
    0.15
     generations
    0.14
     gener
    0.14
     GENER
    0.13
    Activations Density 0.163%

    No Known Activations