© 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. 16065
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "put" and its variations

    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
    bron
    -0.07
    Bron
    -0.07
    aska
    -0.06
    ewe
    -0.06
    restricted
    -0.06
    eson
    -0.06
     Bron
    -0.06
    머
    -0.06
     knock
    -0.06
    aze
    -0.06
    POSITIVE LOGITS
     dend
    0.07
    IDX
    0.07
    eparator
    0.07
     finishing
    0.06
    æĶ¾
    0.06
    _execution
    0.06
    ihan
    0.06
    dür
    0.06
    iche
    0.06
    odies
    0.06
    Activations Density 0.006%

    No Known Activations