© 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. 27290
    Prev
    Next
    INDEX
    Explanations

    elements relating to community-oriented events and services

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

    Tokens that appear in low-quality, potentially machine-generated or spammy content, often at transition points between coherent and incoherent 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
    ynes
    -0.06
    ä¾
    -0.06
     as
    -0.05
    ADVERTISEMENT
    -0.05
    orial
    -0.05
    .in
    -0.05
     bloom
    -0.05
    /reg
    -0.05
     hall
    -0.05
    .↵
    -0.05
    POSITIVE LOGITS
    erdem
    0.10
    ruba
    0.09
    actionDate
    0.08
    lacak
    0.08
    IBUTE
    0.08
    ,strlen
    0.08
    uniacid
    0.08
    groupon
    0.07
    SystemService
    0.07
    marshaller
    0.07
    Activations Density 0.069%

    No Known Activations