© 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. 15-LLAMASCOPE-RES-131K
    11. 61850
    Prev
    Next
    INDEX
    Explanations

    references to prediction or assessment methods in a mystical or psychological context

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

    Words or phrases that form contextual transitions or connections between ideas in text, often appearing in casual writing, forum posts, and articles where the author is explaining concepts or creating narrative flow.

    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
     itk
    -0.06
    ORN
    -0.06
    aption
    -0.06
    ifar
    -0.06
    Ñĥж
    -0.06
    URLException
    -0.06
    veau
    -0.05
    ãĥ¼
    -0.05
    phies
    -0.05
    RIEND
    -0.05
    POSITIVE LOGITS
     Scor
    0.07
     Wheels
    0.07
    ecast
    0.07
     Antar
    0.07
    utex
    0.07
    Wheel
    0.07
    oho
    0.07
    wheel
    0.07
    tdown
    0.06
     Wheel
    0.06
    Activations Density 0.002%

    No Known Activations