© 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. 16641
    Prev
    Next
    INDEX
    Explanations

    occurrences of the prefix "Re" in various contexts

    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
     reap
    -0.06
    athing
    -0.06
     structural
    -0.06
    obox
    -0.06
    osta
    -0.06
    UCT
    -0.06
     recall
    -0.06
     neger
    -0.06
     ZEND
    -0.06
    ัà¸ķà¸ĸ
    -0.06
    POSITIVE LOGITS
    kop
    0.07
    agle
    0.07
    linger
    0.07
    bol
    0.07
    ardon
    0.07
    ourke
    0.07
    noDB
    0.06
    åŁŁ
    0.06
    RTL
    0.06
    ymes
    0.06
    Activations Density 0.016%

    No Known Activations