© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 88227
    Prev
    Next
    INDEX
    Explanations

    references to numerical counts or metrics in the text

    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
    cela
    -0.07
    ků
    -0.07
    ccione
    -0.07
    .wall
    -0.07
    óÅĤ
    -0.07
    ponent
    -0.06
    curity
    -0.06
    vrier
    -0.06
    MOST
    -0.06
    osate
    -0.06
    POSITIVE LOGITS
    enance
    0.16
    DownLatch
    0.12
    =count
    0.11
    erc
    0.11
    ers
    0.09
    inue
    0.09
    /count
    0.09
    ings
    0.09
    ering
    0.09
     noses
    0.09
    Activations Density 0.022%

    No Known Activations