© 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. 93617
    Prev
    Next
    INDEX
    Explanations

    mentions of organizational names or significant events

    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
     пÑĢоÑģ
    -0.07
    ÑĸÑĤÑĥ
    -0.07
    MeasureSpec
    -0.07
    kaar
    -0.06
    ricks
    -0.06
    ÑĢÑıдÑĥ
    -0.06
    stoff
    -0.06
    endedor
    -0.06
    artment
    -0.06
     Danh
    -0.06
    POSITIVE LOGITS
    emet
    0.07
    ugh
    0.07
     began
    0.07
    ina
    0.07
    381
    0.06
    è§
    0.06
    941
    0.06
    deb
    0.06
     fist
    0.06
    ILI
    0.06
    Activations Density 0.004%

    No Known Activations