© 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. 5790
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives that convey emotional or qualitative states

    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
    ocker
    -0.08
    vero
    -0.07
    ixin
    -0.07
    ozor
    -0.07
     dame
    -0.07
    ENTA
    -0.07
    รม
    -0.06
    lep
    -0.06
    pute
    -0.06
     vÃŃde
    -0.06
    POSITIVE LOGITS
    ness
    0.08
    NESS
    0.07
    iores
    0.07
    /plain
    0.07
    itos
    0.07
    ainers
    0.06
    (er
    0.06
    ëĭĪìĬ¤
    0.06
    ervers
    0.06
     thing
    0.06
    Activations Density 0.079%

    No Known Activations