© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4320
    Prev
    Next
    INDEX
    Explanations

    URLs and specific web page reference patterns

    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
     Cald
    -0.09
    esc
    -0.07
    hof
    -0.07
     twe
    -0.07
    ury
    -0.07
    .nih
    -0.06
    vert
    -0.06
    uncio
    -0.06
     tweets
    -0.06
    ÑĤоÑĢ
    -0.06
    POSITIVE LOGITS
    ichel
    0.06
    atos
    0.06
    osite
    0.06
    é£Ľ
    0.06
    .structure
    0.06
    arsed
    0.06
     Raid
    0.06
     баÑĩ
    0.06
     Remark
    0.06
    869
    0.05
    Activations Density 0.007%

    No Known Activations