© 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. 5-LLAMASCOPE-RES-131K
    6. 126032
    Prev
    Next
    INDEX
    Explanations

    references to committees and organizations in a political context

    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
    ahn
    -0.07
     GRAT
    -0.07
    abra
    -0.07
    abil
    -0.07
    fest
    -0.06
    dal
    -0.06
     Peaks
    -0.06
    alth
    -0.06
    ahkan
    -0.06
    ÅĽÄĩ
    -0.06
    POSITIVE LOGITS
    olina
    0.06
    //{{
    0.06
    gener
    0.06
    hend
    0.06
    layui
    0.06
     Blind
    0.06
    ÑĢÑĸÑĩ
    0.06
    ulative
    0.06
     itself
    0.06
    lect
    0.06
    Activations Density 0.001%

    No Known Activations