© 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. 88503
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly those related to measurements and distances

    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
    ozem
    -0.07
    pok
    -0.07
     Ekon
    -0.07
    QueryBuilder
    -0.07
    ected
    -0.07
    sector
    -0.06
    .Escape
    -0.06
    ัà¸ģà¸Ķ
    -0.06
    genesis
    -0.06
    ients
    -0.06
    POSITIVE LOGITS
    utt
    0.07
    oola
    0.07
    roe
    0.06
    ertz
    0.06
    .getJSONArray
    0.06
    (s
    0.06
     proc
    0.06
     wr
    0.06
     advert
    0.05
    insky
    0.05
    Activations Density 0.004%

    No Known Activations