© 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. 56890
    Prev
    Next
    INDEX
    Explanations

    references to fans

    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
    eenth
    -0.09
    cx
    -0.09
    endas
    -0.08
    lef
    -0.08
    ments
    -0.08
    коÑĤ
    -0.08
    mlink
    -0.07
    dux
    -0.07
    naire
    -0.07
    gth
    -0.07
    POSITIVE LOGITS
    atical
    0.11
    atics
    0.09
    atic
    0.09
    fare
    0.09
    /client
    0.08
    eral
    0.08
    boy
    0.07
    erals
    0.07
     Ekon
    0.07
    ouver
    0.07
    Activations Density 0.014%

    No Known Activations