© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 41193
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of "catching" or being caught

    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
    bounce
    -0.07
    adir
    -0.07
    ấu
    -0.07
    ãĥ³ãĥij
    -0.07
    çħ
    -0.07
    icer
    -0.06
    ongyang
    -0.06
    icaret
    -0.06
    à¥Ģà¤Ĥ
    -0.06
    atas
    -0.06
    POSITIVE LOGITS
     caught
    0.10
     catch
    0.10
     catching
    0.10
     catches
    0.09
    caught
    0.09
    Catch
    0.09
     Catch
    0.09
    catch
    0.08
     sight
    0.07
    Caught
    0.07
    Activations Density 0.010%

    No Known Activations