© 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. 9-LLAMASCOPE-RES-131K
    11. 97856
    Prev
    Next
    INDEX
    Explanations

    HTML anchor tags or links in 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
    gado
    -0.09
    pector
    -0.07
    ags
    -0.07
    ÙĨ
    -0.07
    peech
    -0.07
    ContextHolder
    -0.07
    umbotron
    -0.06
    luv
    -0.06
    erin
    -0.06
    umptech
    -0.06
    POSITIVE LOGITS
    MUX
    0.06
    Maker
    0.06
    sher
    0.06
    нем
    0.06
    ıt
    0.06
    Uvs
    0.06
    idente
    0.06
    ardless
    0.06
    URRE
    0.06
    enburg
    0.05
    Activations Density 0.007%

    No Known Activations