© 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. 17-LLAMASCOPE-RES-131K
    11. 76806
    Prev
    Next
    INDEX
    Explanations

    references to information sources and press releases

    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
    idding
    -0.07
    Plus
    -0.06
    mada
    -0.06
    scribed
    -0.06
     MessageType
    -0.06
    ambi
    -0.06
    лек
    -0.06
     Plus
    -0.06
    iqu
    -0.05
     Patt
    -0.05
    POSITIVE LOGITS
     press
    0.11
     Press
    0.09
    press
    0.09
     media
    0.09
     PRESS
    0.09
    Press
    0.08
    -media
    0.08
     MEDIA
    0.08
    media
    0.07
    MEDIA
    0.07
    Activations Density 0.012%

    No Known Activations