© 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. 116767
    Prev
    Next
    INDEX
    Explanations

    elements related to post metadata such as dates and comments

    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
    unsch
    -0.06
     Mundo
    -0.06
    utto
    -0.06
    inç
    -0.05
    stry
    -0.05
     Bless
    -0.05
    uther
    -0.05
    lesia
    -0.05
    ä¿
    -0.05
    omez
    -0.05
    POSITIVE LOGITS
    ãĥĥ
    0.07
    _customize
    0.07
    oj
    0.07
    ÎĨ
    0.06
    /vnd
    0.06
    ÎĪ
    0.06
    erin
    0.06
    ãĥ©ãĤ¤
    0.06
     ”↵↵
    0.06
    (Constructor
    0.06
    Activations Density 0.028%

    No Known Activations