© 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. 98816
    Prev
    Next
    INDEX
    Explanations

    opening and closing braces or curly brackets in structured documents

    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
    lo
    -0.07
    igg
    -0.06
    oley
    -0.06
     dét
    -0.06
    eva
    -0.06
    atz
    -0.06
     suff
    -0.06
     w
    -0.06
    rew
    -0.06
    icated
    -0.06
    POSITIVE LOGITS
    #ad
    0.08
    actionDate
    0.07
    ----------</
    0.07
    .scalablytyped
    0.07
    .dtd
    0.07
    .xr
    0.07
    ¯u
    0.07
    -------------</
    0.07
    коÑĢиÑģÑĤ
    0.07
    ipmap
    0.07
    Activations Density 0.009%

    No Known Activations