© 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. 39555
    Prev
    Next
    INDEX
    Explanations

    biographical information related to birth and personal history

    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
    amel
    -0.06
    leton
    -0.06
    pling
    -0.06
    ¶Į
    -0.06
    udder
    -0.06
     Shake
    -0.06
     Brend
    -0.06
    munition
    -0.06
    .until
    -0.06
    :http
    -0.06
    POSITIVE LOGITS
    oro
    0.07
     Fahr
    0.07
     Juda
    0.06
    empt
    0.06
     akci
    0.06
    olla
    0.06
    acı
    0.06
    _ACT
    0.06
    imestamp
    0.06
    etz
    0.06
    Activations Density 0.001%

    No Known Activations