© 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. 9-LLAMASCOPE-RES-131K
    11. 94827
    Prev
    Next
    INDEX
    Explanations

    terminology related to tax preparation and professionals

    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
    isphere
    -0.07
     Grey
    -0.07
    longleftrightarrow
    -0.06
    ichel
    -0.06
     grey
    -0.06
    ubyte
    -0.06
    rb
    -0.06
    моÑĤ
    -0.06
    esium
    -0.06
     Lis
    -0.06
    POSITIVE LOGITS
    aru
    0.07
    assist
    0.07
    dw
    0.07
    idUser
    0.06
    aber
    0.06
     Assist
    0.06
    enef
    0.06
    763
    0.06
    WithOptions
    0.06
    abi
    0.06
    Activations Density 0.002%

    No Known Activations