© 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. 15-LLAMASCOPE-RES-131K
    11. 85982
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and expressions related to timing or sequences

    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
    ł
    -0.07
    ãĥ¼ãĥĨ
    -0.06
    ugas
    -0.06
    087
    -0.06
    freeze
    -0.06
     bounty
    -0.05
    cla
    -0.05
    }->
    -0.05
    ì°°
    -0.05
    PMC
    -0.05
    POSITIVE LOGITS
    eva
    0.07
    rah
    0.07
    524
    0.07
    enha
    0.07
    EDA
    0.06
    ¶Ī
    0.06
    oad
    0.06
    _PLL
    0.06
     Wonderland
    0.06
    olla
    0.06
    Activations Density 0.017%

    No Known Activations