© 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. 40832
    Prev
    Next
    INDEX
    Explanations

    instances of structured information or numerical data

    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
     turist
    -0.07
    uisse
    -0.07
     yacc
    -0.07
    serrat
    -0.07
     ëĦ¤ìĿ´íĬ¸
    -0.07
    chantment
    -0.07
    prech
    -0.07
    ilim
    -0.07
    iqueta
    -0.07
    foreign
    -0.07
    POSITIVE LOGITS
     feudal
    0.06
     Brilliant
    0.06
     Imperial
    0.06
    리ìĸ´
    0.06
     Conf
    0.06
     clan
    0.05
    èĸ¬
    0.05
     Drum
    0.05
     POV
    0.05
     sug
    0.05
    Activations Density 0.000%

    No Known Activations