© 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. 128991
    Prev
    Next
    INDEX
    Explanations

    terms related to "catch" 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
    arily
    -0.07
    arity
    -0.07
    pton
    -0.07
    stk
    -0.07
    ize
    -0.07
    ashes
    -0.07
    itä
    -0.07
    arians
    -0.07
    ÑģÑĮ
    -0.07
    orphic
    -0.07
    POSITIVE LOGITS
    phrase
    0.10
    ess
    0.08
    back
    0.08
     catching
    0.07
    ness
    0.07
    rap
    0.07
    itan
    0.07
    woord
    0.07
     Catch
    0.07
    down
    0.07
    Activations Density 0.014%

    No Known Activations