© 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 EvalsExportsinterp-engineNEWAPI 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. 39041
    Prev
    Next
    INDEX
    Explanations

    frequency of past tense verbs and their usage in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ark
    -0.06
    urt
    -0.06
     experience
    -0.06
    dar
    -0.06
    rine
    -0.06
    oad
    -0.06
    rr
    -0.06
    berger
    -0.06
    âĶģ
    -0.06
    arken
    -0.06
    POSITIVE LOGITS
    ecast
    0.08
    ripp
    0.08
    ohl
    0.07
    epy
    0.07
    leck
    0.07
    ecies
    0.07
    dbh
    0.07
    eca
    0.07
    entai
    0.06
    _Widget
    0.06
    Activations Density 0.025%

    No Known Activations