© 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. 54568
    Prev
    Next
    INDEX
    Explanations

    references to argumentation or debate

    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
    iges
    -0.08
    zsche
    -0.07
    staking
    -0.07
    oming
    -0.07
    apo
    -0.07
    ngrx
    -0.07
    одÑĥ
    -0.07
    ech
    -0.07
    LY
    -0.07
    bsd
    -0.07
    POSITIVE LOGITS
    uably
    0.10
    entina
    0.07
    inine
    0.07
    ÑĥменÑĤ
    0.07
    uing
    0.07
    emma
    0.07
    entine
    0.07
    aine
    0.07
    onaut
    0.07
    ipel
    0.06
    Activations Density 0.007%

    No Known Activations