© 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. 118120
    Prev
    Next
    INDEX
    Explanations

    mentions of academic or educational contexts

    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
     impress
    -0.06
    akov
    -0.06
     attract
    -0.06
     wedge
    -0.06
    /comment
    -0.06
    ãĤīãģĹ
    -0.06
    [to
    -0.05
     Resets
    -0.05
    ái
    -0.05
    [*
    -0.05
    POSITIVE LOGITS
    culus
    0.07
    fy
    0.07
     Mezi
    0.07
    apos
    0.07
    iband
    0.07
    errick
    0.07
    illion
    0.07
    urat
    0.07
    иÑģлов
    0.06
    umm
    0.06
    Activations Density 0.022%

    No Known Activations