© 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. 9-LLAMASCOPE-RES-131K
    11. 99032
    Prev
    Next
    INDEX
    Explanations

    instances of null and false boolean values

    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
    .wr
    -0.07
    одÑĭ
    -0.06
    ffd
    -0.06
    Coding
    -0.06
    quiry
    -0.06
    ewis
    -0.06
    leur
    -0.06
    uration
    -0.06
    noinspection
    -0.06
    toArray
    -0.06
    POSITIVE LOGITS
    eko
    0.07
    ipel
    0.06
    ÙĦس
    0.06
    PARATOR
    0.06
    gua
    0.06
    647
    0.06
     photoc
    0.06
    umble
    0.06
    DG
    0.06
    PILE
    0.05
    Activations Density 0.019%

    No Known Activations