© 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 EvalsExportsinterp-engineNEWAPI 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. 70636
    Prev
    Next
    INDEX
    Explanations

    non-alphanumeric characters or symbols within the text

    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
    s
    -0.11
    en
    -0.09
    Ùĩ
    -0.09
    hiro
    -0.09
    и
    -0.09
    e
    -0.08
    i
    -0.07
    htags
    -0.07
    arters
    -0.07
    a
    -0.07
    POSITIVE LOGITS
    igr
    0.07
    omes
    0.07
    iland
    0.06
    ãĥ³ãĥ
    0.06
    amer
    0.06
    rement
    0.06
    inn
    0.06
    νοÏį
    0.06
    icer
    0.06
    umer
    0.06
    Activations Density 0.027%

    No Known Activations