© 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. 88531
    Prev
    Next
    INDEX
    Explanations

    statistical measures such as averages and means in datasets

    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
    /tos
    -0.08
    reator
    -0.07
     Mort
    -0.07
    _DIGEST
    -0.07
    NECT
    -0.07
    /stretch
    -0.07
    fty
    -0.07
    ãĥ©ãĥĥãĤ¯
    -0.07
    _defaults
    -0.06
    wiki
    -0.06
    POSITIVE LOGITS
     age
    0.06
    yst
    0.06
    raki
    0.06
    y
    0.06
    -age
    0.06
    om
    0.06
    ja
    0.06
    yas
    0.06
    iga
    0.06
    osaurs
    0.06
    Activations Density 0.018%

    No Known Activations