© 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. 78384
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "in" contextualized within historical or architectural descriptions

    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
    //{{
    -0.07
    Slug
    -0.07
    @param
    -0.07
    reas
    -0.07
    ocht
    -0.07
    enheim
    -0.07
    AGMA
    -0.07
    ÙĨÛĮÙĨ
    -0.07
    orsch
    -0.07
    pell
    -0.07
    POSITIVE LOGITS
    ucene
    0.07
    0.06
    ingo
    0.06
    warf
    0.06
    åį«
    0.06
    _ABC
    0.06
     style
    0.06
    197
    0.06
    æĿIJ
    0.06
    AINS
    0.06
    Activations Density 0.009%

    No Known Activations