© 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. 9-LLAMASCOPE-RES-131K
    11. 95515
    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
    bean
    -0.08
    allee
    -0.07
    mlin
    -0.06
    Bean
    -0.06
    pt
    -0.06
    ies
    -0.06
    ancell
    -0.06
    ettel
    -0.06
    âĢ¦
    -0.06
    mue
    -0.06
    POSITIVE LOGITS
    Drv
    0.07
     blackmail
    0.07
    _below
    0.07
    मन
    0.06
     Bapt
    0.06
    uum
    0.06
     putas
    0.06
    arton
    0.06
    è
    0.06
     dikke
    0.06
    Activations Density 0.000%

    No Known Activations