© 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. 14106
    Prev
    Next
    INDEX
    Explanations

    expressions or phrases associated with tactile experiences or the concept of 'touch' in various contexts

    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
    theless
    -0.08
    hea
    -0.07
    imum
    -0.07
    Ñıл
    -0.07
    bons
    -0.07
    Bonjour
    -0.07
    ishly
    -0.07
    ALLY
    -0.07
    nesia
    -0.07
    amente
    -0.07
    POSITIVE LOGITS
    (es
    0.11
    mere
    0.09
    erman
    0.08
    screens
    0.08
    pad
    0.08
    stone
    0.08
    point
    0.08
    yc
    0.07
    less
    0.07
    able
    0.07
    Activations Density 0.009%

    No Known Activations