© 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. 80613
    Prev
    Next
    INDEX
    Explanations

    specific character names or significant identifiers within narratives

    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
    _COMPAT
    -0.08
    Äįást
    -0.07
    кÑĢа
    -0.07
     Mezi
    -0.07
    ASTER
    -0.07
    нож
    -0.07
    á»ĭp
    -0.07
    ãĥĨãĥ«
    -0.07
    ï¼
    -0.06
    MUX
    -0.06
    POSITIVE LOGITS
    imum
    0.06
     tomorrow
    0.06
    ĵ
    0.06
    ibly
    0.06
     
    0.06
     strang
    0.06
    ets
    0.05
    loquent
    0.05
    iiii
    0.05
     YOUR
    0.05
    Activations Density 0.007%

    No Known Activations