© 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. 26834
    Prev
    Next
    INDEX
    Explanations

    terms related to roofing issues and the necessity of replacement or repair

    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
    POSIT
    -0.07
    alm
    -0.06
     ex
    -0.06
    wald
    -0.06
    827
    -0.06
     lạc
    -0.06
    óm
    -0.06
    ://{
    -0.06
    éĢł
    -0.05
    à¥Īद
    -0.05
    POSITIVE LOGITS
    AREST
    0.08
    umar
    0.07
     professionnel
    0.07
     immedi
    0.07
     immediately
    0.07
    emailer
    0.07
     immediate
    0.07
    anje
    0.07
    -remove
    0.06
    vestment
    0.06
    Activations Density 0.008%

    No Known Activations