© 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. 118812
    Prev
    Next
    INDEX
    Explanations

    URLs and links related to GitHub repositories

    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
    bih
    -0.07
    hsi
    -0.07
    unken
    -0.07
    ее
    -0.06
    assa
    -0.06
    fü
    -0.06
    одÑĭ
    -0.06
    aside
    -0.06
    gere
    -0.06
     kesin
    -0.06
    POSITIVE LOGITS
    aison
    0.07
     Curtis
    0.06
    fol
    0.06
    opensource
    0.06
     Lace
    0.06
     Brock
    0.06
    Qualifier
    0.06
     Simpl
    0.06
     Ak
    0.06
    acea
    0.06
    Activations Density 0.008%

    No Known Activations