© 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 EvalsExportsAPI 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. 40496
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "for."

    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
    odelist
    -0.06
     DC
    -0.06
    ffi
    -0.06
    ül
    -0.06
     Hang
    -0.05
    .microsoft
    -0.05
    ecz
    -0.05
    Ùıع
    -0.05
    .getLine
    -0.05
     minim
    -0.05
    POSITIVE LOGITS
    593
    0.07
     Bart
    0.07
    oyer
    0.07
     Banc
    0.06
    aldi
    0.06
    alc
    0.06
    ario
    0.06
     banc
    0.06
    596
    0.06
    γÏĮ
    0.06
    Activations Density 0.000%

    No Known Activations