Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95978
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically periods

    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
     S
    -0.06
     u
    -0.06
     Kurt
    -0.05
    ,
    -0.05
     (
    -0.05
    (
    -0.05
     E
    -0.05
    GT
    -0.05
     Mil
    -0.05
     ag
    -0.05
    POSITIVE LOGITS
    okino
    0.08
    RITE
    0.07
    anik
    0.07
    _LP
    0.07
    .GroupLayout
    0.07
    -equiv
    0.07
    oại
    0.07
     meis
    0.07
    odos
    0.07
    (Scene
    0.07
    Activations Density 0.000%

    No Known Activations