© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 103908
    Prev
    Next
    INDEX
    Explanations

    instances of the word "rush" and its variations 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
    ãģ¥
    -0.08
    isplay
    -0.08
    son
    -0.08
    utow
    -0.08
    ever
    -0.08
    izabeth
    -0.08
    ahren
    -0.07
    sons
    -0.07
    oshi
    -0.07
    hin
    -0.07
    POSITIVE LOGITS
    (es
    0.11
    es
    0.09
    ingly
    0.07
    inder
    0.07
    esin
    0.07
    aby
    0.06
    mallow
    0.06
    fold
    0.06
    pal
    0.06
    ower
    0.06
    Activations Density 0.006%

    No Known Activations