© 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. 63171
    Prev
    Next
    INDEX
    Explanations

    references to various forms of damage, both physical and metaphorical

    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
    ropa
    -0.09
    rose
    -0.08
    iaux
    -0.07
    lland
    -0.07
    IFI
    -0.07
    nesday
    -0.07
     adipiscing
    -0.07
    iew
    -0.07
    irie
    -0.07
    swith
    -0.07
    POSITIVE LOGITS
    acias
    0.07
    aceutical
    0.07
    adol
    0.07
    -free
    0.07
    greg
    0.06
    ะ
    0.06
    lessly
    0.06
    proof
    0.06
    immune
    0.06
    åĻ¨
    0.06
    Activations Density 0.012%

    No Known Activations