© 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. 16335
    Prev
    Next
    INDEX
    Explanations

    programming-related descriptions or representations of objects

    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
     crew
    -0.06
    crew
    -0.05
     cater
    -0.05
    ب
    -0.05
     parallel
    -0.05
     Crew
    -0.05
    parallel
    -0.05
     f
    -0.05
    -0.05
     physically
    -0.05
    POSITIVE LOGITS
     representation
    0.09
     Representation
    0.09
    ahy
    0.09
    Representation
    0.08
    á»Ļ
    0.08
    representation
    0.08
     representations
    0.08
    616
    0.07
    APSHOT
    0.07
    íķĻ기
    0.07
    Activations Density 0.002%

    No Known Activations