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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 120400
    Prev
    Next
    INDEX
    Explanations

    references to Congress and its related activities or legislation

    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
    uhe
    -0.07
    resden
    -0.07
    ÅĽmy
    -0.07
    steen
    -0.07
    achten
    -0.07
    ÑİÑĢ
    -0.07
    etros
    -0.07
    lopen
    -0.07
    ÑĨе
    -0.07
    ombok
    -0.07
    POSITIVE LOGITS
    ional
    0.12
    ion
    0.09
    es
    0.08
    s
    0.08
    ions
    0.08
    woman
    0.08
    ible
    0.07
    ures
    0.07
    rooms
    0.07
    man
    0.07
    Activations Density 0.011%

    No Known Activations