© 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. 17-LLAMASCOPE-RES-131K
    6. 119132
    Prev
    Next
    INDEX
    Explanations

    informal speech patterns and filler words

    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
    afort
    -0.08
    esy
    -0.07
    Winvalid
    -0.07
    ument
    -0.07
    #
    -0.07
    (æľ¨
    -0.07
    umberland
    -0.07
    	Copyright
    -0.07
    ONT
    -0.07
    illance
    -0.07
    POSITIVE LOGITS
    ellan
    0.06
     Mane
    0.06
    iti
    0.06
    977
    0.06
    hua
    0.05
    ata
    0.05
    ิà¸ĺ
    0.05
    _hosts
    0.05
    rog
    0.05
    377
    0.05
    Activations Density 0.014%

    No Known Activations