© 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. 77569
    Prev
    Next
    INDEX
    Explanations

    programming and authentication-related actions

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

    Verbs used as programming function names or methods that typically perform transformative operations on data.

    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
    ness
    -0.11
    sWith
    -0.10
    nya
    -0.09
    Ø©
    -0.09
    rens
    -0.08
    ality
    -0.08
    rec
    -0.08
    lands
    -0.08
    so
    -0.08
    ìĿĦ
    -0.08
    POSITIVE LOGITS
    able
    0.14
    ments
    0.12
    ings
    0.11
    ables
    0.10
    ability
    0.10
    ÂŃing
    0.10
    cation
    0.09
    ances
    0.09
    ABLE
    0.09
    MENT
    0.09
    Activations Density 0.135%

    No Known Activations