© 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. 17-LLAMASCOPE-RES-131K
    11. 118115
    Prev
    Next
    INDEX
    Explanations

    phrases indicating denial of wrongdoing or conspiracy theories

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

    Explanatory text revealing the reasoning, justification, or context behind actions, decisions, or policies, often in quoted statements from officials or reports.

    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
    itler
    -0.09
     Uncategorized
    -0.09
    bject
    -0.08
    agher
    -0.08
    ..↵↵↵↵
    -0.08
    buat
    -0.08
    ãĥ»ãĥ»ãĥ»↵↵
    -0.08
    ılıģıyla
    -0.07
    asal
    -0.07
    ,)↵
    -0.07
    POSITIVE LOGITS
     [âĢ¦]
    0.12
    [,]
    0.11
    %C
    0.10
    [s
    0.10
     [âĢ¦
    0.10
     [=
    0.10
    [d
    0.09
     [_
    0.09
     [...]↵↵
    0.08
     [`
    0.08
    Activations Density 10.109%

    No Known Activations