© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 103730
    Prev
    Next
    INDEX
    Explanations

    editorial content and discussions related to governance or political opinions

    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
    andler
    -0.07
    abad
    -0.07
    pled
    -0.06
    ampo
    -0.06
     Pist
    -0.06
    gu
    -0.06
    ระà¹Ģà¸ļ
    -0.06
    ostringstream
    -0.06
     å¿
    -0.06
    SerializedName
    -0.06
    POSITIVE LOGITS
     Editorial
    0.10
     editorial
    0.10
     editors
    0.07
    .Op
    0.07
    editor
    0.07
     Hoy
    0.07
     Editors
    0.07
    TEAM
    0.06
     bulk
    0.06
     our
    0.06
    Activations Density 0.011%

    No Known Activations