© 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. 96102
    Prev
    Next
    INDEX
    Explanations

    technical specifications and parameters related to electrical and mechanical systems

    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
    irit
    -0.06
     woman
    -0.06
    ForRow
    -0.06
     nth
    -0.06
    iddi
    -0.05
     volume
    -0.05
     real
    -0.05
     mul
    -0.05
    ç¯Ģ
    -0.05
    ovel
    -0.05
    POSITIVE LOGITS
    они
    0.07
    ãĤ¶ãĥ¼
    0.07
    belt
    0.07
    ount
    0.07
    _wr
    0.07
    ROUGH
    0.07
    mounted
    0.07
     punches
    0.06
    kla
    0.06
    125
    0.06
    Activations Density 0.002%

    No Known Activations