© 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. 40994
    Prev
    Next
    INDEX
    Explanations

    references to government bodies and officials

    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
    est
    -0.07
    inese
    -0.06
    lap
    -0.06
    x
    -0.06
    ahlen
    -0.06
    aft
    -0.06
    crew
    -0.06
    ulia
    -0.06
    andin
    -0.06
    ize
    -0.06
    POSITIVE LOGITS
    ÑĢап
    0.07
     President
    0.07
     president
    0.07
    ạo
    0.07
    Ħĸ
    0.07
     opr
    0.07
     ØŃد
    0.07
    _dx
    0.07
    ayload
    0.07
    idth
    0.07
    Activations Density 0.009%

    No Known Activations