© 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 EvalsExportsAPI 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. 88610
    Prev
    Next
    INDEX
    Explanations

    occurrences of a specific name or term, particularly related to a person or subject of interest

    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
    edBy
    -0.06
     Pow
    -0.06
    raph
    -0.06
    ãĥ¥
    -0.06
    ans
    -0.06
    ado
    -0.06
    259
    -0.06
    zer
    -0.06
    uning
    -0.06
    isse
    -0.05
    POSITIVE LOGITS
    phabet
    0.09
    SCII
    0.08
    abox
    0.07
    æĤł
    0.07
    eyin
    0.07
    коз
    0.07
    mÃŃ
    0.07
    eral
    0.07
     æĶ¾
    0.07
    isine
    0.07
    Activations Density 0.006%

    No Known Activations