© 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. 60989
    Prev
    Next
    INDEX
    Explanations

    references to publication years and citations

    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
    alars
    -0.08
    cae
    -0.08
    ourt
    -0.07
    enever
    -0.07
    apons
    -0.07
    jac
    -0.07
    оÑĢони
    -0.07
    ButtonItem
    -0.06
    podob
    -0.06
    #
    -0.06
    POSITIVE LOGITS
    199
    0.10
    200
    0.09
    198
    0.09
    197
    0.07
    adera
    0.06
    201
    0.06
    yles
    0.06
     Lantern
    0.06
    qw
    0.06
     Shack
    0.06
    Activations Density 0.037%

    No Known Activations