© 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. 29517
    Prev
    Next
    INDEX
    Explanations

    imperative phrases and recommendations for action

    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
    ileo
    -0.07
    rax
    -0.07
    ught
    -0.06
    egend
    -0.06
     weiber
    -0.06
    kö
    -0.06
    á»įt
    -0.06
    rive
    -0.06
    лами
    -0.06
    aight
    -0.06
    POSITIVE LOGITS
     consider
    0.07
    à¸ĩศ
    0.07
    SizePolicy
    0.07
     consideration
    0.06
     limit
    0.06
    ãģĹãģ¾
    0.06
     stol
    0.06
     Hra
    0.06
    å¦
    0.06
     misunder
    0.06
    Activations Density 0.022%

    No Known Activations