© 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. 104130
    Prev
    Next
    INDEX
    Explanations

    phrases indicating intention or purpose

    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
    rve
    -0.08
    .rs
    -0.07
    ä¸Ī
    -0.07
    rvé
    -0.07
    issan
    -0.07
    $core
    -0.07
    geh
    -0.07
    ãĥ³ãĥķ
    -0.07
    .lex
    -0.07
    luet
    -0.07
    POSITIVE LOGITS
    ond
    0.07
     be
    0.07
    idi
    0.07
    BN
    0.06
    ounty
    0.06
     themselves
    0.06
    uman
    0.06
     come
    0.06
    lay
    0.06
    CODE
    0.05
    Activations Density 0.063%

    No Known Activations