© 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. 61483
    Prev
    Next
    INDEX
    Explanations

    elements of dark humor and absurdity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Punctuation marks and connecting phrases that serve as natural transition points between separate ideas or sections of text.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    atto
    -0.08
    obra
    -0.07
    ordion
    -0.07
     Sass
    -0.07
    ournal
    -0.07
    uw
    -0.06
     pack
    -0.06
    à¹Ĥà¸ģ
    -0.06
    eeper
    -0.06
    ató
    -0.06
    POSITIVE LOGITS
     Nor
    0.10
     nor
    0.09
     unless
    0.08
    unless
    0.08
     merely
    0.08
    Nor
    0.07
     except
    0.07
     NOR
    0.07
    >Main
    0.07
    except
    0.07
    Activations Density 0.038%

    No Known Activations