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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-LLAMASCOPE-RES-131K
    6. 95951
    Prev
    Next
    INDEX
    Explanations

    terms related to governmental and legal institutions

    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
    kus
    -0.07
    ypes
    -0.07
    yp
    -0.07
    vern
    -0.07
    itele
    -0.06
    amus
    -0.06
    orca
    -0.06
    acam
    -0.06
    .nano
    -0.06
    ÑĢÑĥÑĪ
    -0.06
    POSITIVE LOGITS
    656
    0.07
     Morgan
    0.06
    ipay
    0.06
     bows
    0.06
    )throws
    0.05
    é¥Ń
    0.05
    andal
    0.05
    106
    0.05
    ike
    0.05
    rades
    0.05
    Activations Density 0.016%

    No Known Activations