© 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. 15-LLAMASCOPE-RES-131K
    11. 26862
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting symbols in a programming context

    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
    zelf
    -0.07
     underway
    -0.06
    -kind
    -0.06
    tml
    -0.06
    isine
    -0.06
    uellement
    -0.06
    cis
    -0.06
    ÙĦØŃ
    -0.06
    UNET
    -0.06
    olik
    -0.06
    POSITIVE LOGITS
    umar
    0.06
    cline
    0.06
     oby
    0.06
    üml
    0.06
    à¥įबर
    0.06
    kili
    0.06
    ecc
    0.06
    å¢
    0.06
    itage
    0.06
    _PRIMARY
    0.06
    Activations Density 0.023%

    No Known Activations