© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 69890
    Prev
    Next
    INDEX
    Explanations

    phrases related to directives and credit attribution in content creation

    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
    .scalablytyped
    -0.08
    utsch
    -0.07
    odef
    -0.07
    FormattedMessage
    -0.07
    lander
    -0.07
    _FILENO
    -0.07
    gressive
    -0.07
    κÏģα
    -0.07
    .bunifuFlatButton
    -0.06
    gress
    -0.06
    POSITIVE LOGITS
     credits
    0.09
     credit
    0.07
     attribution
    0.07
    credits
    0.07
     acknowledge
    0.07
     credited
    0.07
     acknowledgement
    0.07
     Hell
    0.07
    rops
    0.07
    bows
    0.06
    Activations Density 0.020%

    No Known Activations