© 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. 93754
    Prev
    Next
    INDEX
    Explanations

    terms related to data collection and privacy

    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
    ahat
    -0.07
    otland
    -0.07
    TRANSFER
    -0.06
    çĨ
    -0.06
    ForResult
    -0.06
    amı
    -0.06
    /cards
    -0.06
     Seat
    -0.06
    è§
    -0.06
    iband
    -0.06
    POSITIVE LOGITS
    ors
    0.07
     rain
    0.06
    ãĥ¼ãĥ«
    0.06
     merk
    0.06
     wet
    0.06
    ORS
    0.06
    ritz
    0.06
    à¤Ĥà¤ķ
    0.06
    зÑĭ
    0.06
    алеж
    0.06
    Activations Density 0.001%

    No Known Activations