© 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. 93511
    Prev
    Next
    INDEX
    Explanations

    statements emphasizing the importance of support and recognition in the arts

    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
     therefore
    -0.07
    TEMPL
    -0.07
    esco
    -0.07
    ASC
    -0.07
     wiÄĻc
    -0.07
    IXEL
    -0.07
    aille
    -0.07
    rous
    -0.07
    ota
    -0.06
    avings
    -0.06
    POSITIVE LOGITS
    æ¯ķ
    0.08
    -away
    0.07
     Away
    0.07
    аÑĢаÑĤ
    0.07
    since
    0.07
     ведÑĮ
    0.06
    amos
    0.06
    Away
    0.06
     ли
    0.06
    Es
    0.06
    Activations Density 0.034%

    No Known Activations