© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 116447
    Prev
    Next
    INDEX
    Explanations

    phrases related to manipulation and deceptive narratives

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    amina
    -0.06
    360
    -0.06
    egrity
    -0.06
    usz
    -0.06
    ifs
    -0.06
    uz
    -0.06
    UZ
    -0.05
    368
    -0.05
    æIJŃ
    -0.05
    ambi
    -0.05
    POSITIVE LOGITS
     justification
    0.09
     justify
    0.08
    _argument
    0.07
    iteDatabase
    0.07
     argument
    0.07
    hev
    0.07
    ldre
    0.07
    apos
    0.07
    argument
    0.06
    ftype
    0.06
    Activations Density 0.054%

    No Known Activations