© 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. 89594
    Prev
    Next
    INDEX
    Explanations

    statements presenting ideas or intentions, particularly those starting with "the goal is."

    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
     its
    -0.07
    esz
    -0.06
     une
    -0.06
    uya
    -0.06
    ulence
    -0.06
     clam
    -0.06
    /to
    -0.05
    raud
    -0.05
    eam
    -0.05
     w
    -0.05
    POSITIVE LOGITS
     ÑĩÑĤобÑĭ
    0.08
    .matcher
    0.07
     Ekon
    0.07
    .mesh
    0.07
    azio
    0.07
    oton
    0.07
    Ctrls
    0.07
    íģ
    0.07
    rust
    0.06
    .updateDynamic
    0.06
    Activations Density 0.011%

    No Known Activations