© 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. 83513
    Prev
    Next
    INDEX
    Explanations

    the character "a" in various contexts and repetitions throughout the document

    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
    egg
    -0.07
    aukee
    -0.07
    aso
    -0.07
    469
    -0.07
    keh
    -0.06
    åºľ
    -0.06
    ob
    -0.06
    γο
    -0.06
    velt
    -0.06
    allet
    -0.06
    POSITIVE LOGITS
    Ī
    0.07
    remium
    0.07
    oler
    0.06
    atrix
    0.06
    gressive
    0.06
    ereco
    0.06
    reta
    0.06
    emem
    0.06
    longleftrightarrow
    0.06
    classname
    0.06
    Activations Density 0.011%

    No Known Activations