© 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. 74920
    Prev
    Next
    INDEX
    Explanations

    occurrences of punctuation marks and structural elements within the text

    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
     Tra
    -0.07
    arton
    -0.06
    ices
    -0.06
    IES
    -0.06
    ess
    -0.06
    at
    -0.06
     pen
    -0.06
    ylan
    -0.06
    ice
    -0.06
    Tra
    -0.06
    POSITIVE LOGITS
     neod
    0.07
    üle
    0.07
    PURE
    0.07
    ?url
    0.07
    ensburg
    0.07
    udeau
    0.06
    ÏĩÏģι
    0.06
    .dds
    0.06
    ROC
    0.06
    Margins
    0.06
    Activations Density 0.001%

    No Known Activations