© 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. 15-LLAMASCOPE-RES-131K
    11. 0
    Prev
    Next
    INDEX
    Explanations

    occurrences of the preposition "by."

    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
    incinn
    -0.08
    esti
    -0.07
    onth
    -0.07
    -INF
    -0.07
    ivity
    -0.07
    remember
    -0.06
    arend
    -0.06
    yyy
    -0.06
    orman
    -0.06
    paren
    -0.06
    POSITIVE LOGITS
     how
    0.10
    unker
    0.08
    how
    0.07
     prospects
    0.07
     cómo
    0.07
    ìĦ¸
    0.06
     what
    0.06
    iyan
    0.06
    rine
    0.06
    ipel
    0.06
    Activations Density 0.018%

    No Known Activations