Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5523
    Prev
    Next
    INDEX
    Explanations

    instances of political reluctance and challenges in program implementation

    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
    iyon
    -0.08
    avax
    -0.07
    eldo
    -0.07
     respectfully
    -0.07
    ansen
    -0.07
    iasi
    -0.07
    æľŃ
    -0.07
    }č↵č↵č↵č↵
    -0.07
    osaic
    -0.06
     Sokol
    -0.06
    POSITIVE LOGITS
     any
    0.11
     anything
    0.09
     confrontation
    0.09
     directly
    0.08
     direct
    0.08
     robust
    0.08
     anymore
    0.08
     overt
    0.08
     explicit
    0.08
     too
    0.08
    Activations Density 0.056%

    No Known Activations