© 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. 15-LLAMASCOPE-RES-131K
    11. 88739
    Prev
    Next
    INDEX
    Explanations

    references to author names and their affiliations in academic publications

    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
    kara
    -0.07
    вай
    -0.07
     beled
    -0.06
    ¶Į
    -0.06
     ,[
    -0.06
    коп
    -0.06
    .fm
    -0.06
    лÑİд
    -0.06
    ecut
    -0.06
    ÄĽj
    -0.06
    POSITIVE LOGITS
    java
    0.07
    ocks
    0.07
    utr
    0.06
    uto
    0.06
    avra
    0.06
    illis
    0.06
    olum
    0.06
    ãĤ¿ãĥ«
    0.06
    edReader
    0.06
    amm
    0.06
    Activations Density 0.002%

    No Known Activations