© 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. 1982
    Prev
    Next
    INDEX
    Explanations

    interactions and changes related to colors and visual representations in a user interface

    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
    urban
    -0.07
    ofilm
    -0.07
    /manage
    -0.07
    æ¢
    -0.06
    é¢
    -0.06
    BindingUtil
    -0.06
    /firebase
    -0.06
    jah
    -0.06
    awi
    -0.06
    abbr
    -0.06
    POSITIVE LOGITS
     outline
    0.08
     indication
    0.07
     hil
    0.07
    indic
    0.07
    :animated
    0.07
    ÑĤаж
    0.07
     inplace
    0.06
     indic
    0.06
     indicating
    0.06
    instein
    0.06
    Activations Density 0.014%

    No Known Activations