© 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. 119279
    Prev
    Next
    INDEX
    Explanations

    references to individuals providing testimony or observations

    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
    asan
    -0.09
    adesh
    -0.09
    asar
    -0.08
    ERIC
    -0.08
    ady
    -0.08
    igi
    -0.08
    aign
    -0.08
    adiens
    -0.08
    iminal
    -0.07
    spa
    -0.07
    POSITIVE LOGITS
    ry
    0.09
    ess
    0.09
    ively
    0.07
    (es
    0.07
    RY
    0.07
    dom
    0.06
    marshal
    0.06
    ย
    0.06
    arrant
    0.06
    es
    0.06
    Activations Density 0.005%

    No Known Activations