© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 29796
    Prev
    Next
    INDEX
    Explanations

    occurrence of the word "title" and related HTML title elements in the document

    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
    acco
    -0.07
    ours
    -0.07
    ills
    -0.07
     trade
    -0.06
    azz
    -0.06
    cil
    -0.06
    ajs
    -0.06
    PO
    -0.06
    IDA
    -0.06
    bedo
    -0.06
    POSITIVE LOGITS
    /WebAPI
    0.07
    reesome
    0.06
     fran
    0.06
    लà¤Ĺ
    0.06
    uC
    0.06
    -toggler
    0.06
    RAINT
    0.06
    rew
    0.06
    ãĤ¿ãĤ¤
    0.06
    .asm
    0.06
    Activations Density 0.001%

    No Known Activations