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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3804
    Prev
    Next
    INDEX
    Explanations

    topics related to art and religious themes

    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
    isel
    -0.09
    opp
    -0.08
    eil
    -0.07
    uh
    -0.07
    ogg
    -0.07
    tg
    -0.07
    rish
    -0.07
    allet
    -0.07
    allel
    -0.06
    _________________↵↵
    -0.06
    POSITIVE LOGITS
     RuntimeObject
    0.07
    uteur
    0.07
    /WebAPI
    0.06
    bib
    0.06
     EITHER
    0.06
    igua
    0.06
    thood
    0.06
    OTHER
    0.06
    над
    0.06
     dub
    0.06
    Activations Density 0.004%

    No Known Activations