© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 76625
    Prev
    Next
    INDEX
    Explanations

    instances or phrases related to specific business or financial transactions

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

    Sentence-final periods that conclude factual statements in formal, informational 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
    oder
    -0.07
     otherwise
    -0.07
    -0.06
     but
    -0.06
     every
    -0.06
     Hem
    -0.06
     any
    -0.06
     hem
    -0.06
     for
    -0.06
     even
    -0.06
    POSITIVE LOGITS
    ypse
    0.09
    zzle
    0.09
    imdi
    0.09
    'gc
    0.09
    .TRAN
    0.09
    бÑĭ
    0.08
    JEXEC
    0.08
    anship
    0.08
    hlen
    0.08
    ANTE
    0.08
    Activations Density 0.054%

    No Known Activations