© 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. 116331
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to sensory experiences and sensations

    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
    .scalablytyped
    -0.09
    stery
    -0.08
    uments
    -0.08
    isas
    -0.08
    anh
    -0.08
    uner
    -0.07
    ffen
    -0.07
    isle
    -0.07
    otte
    -0.07
    anger
    -0.07
    POSITIVE LOGITS
    esh
    0.07
    ory
    0.06
    115
    0.06
    lessly
    0.06
    awe
    0.06
    cape
    0.06
    i
    0.06
    iar
    0.06
    esto
    0.06
    ron
    0.06
    Activations Density 0.007%

    No Known Activations