© 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. 97318
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "any."

    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
    arrants
    -0.06
    opoulos
    -0.06
    ycl
    -0.06
    ови
    -0.06
    ircuit
    -0.06
    òa
    -0.06
     Hicks
    -0.06
    .Condition
    -0.06
    بÙĦ
    -0.06
    irie
    -0.06
    POSITIVE LOGITS
    ç£
    0.07
    undi
    0.07
    972
    0.06
    hte
    0.06
    تÙĪر
    0.06
     ìĿ´ëĬĶ
    0.06
    ñana
    0.06
    ecta
    0.06
    ubar
    0.06
    CM
    0.06
    Activations Density 0.003%

    No Known Activations