© 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. 16583
    Prev
    Next
    INDEX
    Explanations

    phrases related to voting and approval processes

    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
     annonces
    -0.08
    _Pin
    -0.08
    ober
    -0.07
    abant
    -0.07
     PROCUREMENT
    -0.07
    æĴ
    -0.07
    robat
    -0.07
    ASI
    -0.07
    ops
    -0.06
    ?↵↵↵↵↵↵
    -0.06
    POSITIVE LOGITS
     shall
    0.08
    adero
    0.07
    pec
    0.06
     Rack
    0.06
    stead
    0.06
    shall
    0.06
    еÑĢеÑĩ
    0.06
     reasonably
    0.06
     conc
    0.06
    istencia
    0.06
    Activations Density 0.782%

    No Known Activations