© 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. 91525
    Prev
    Next
    INDEX
    Explanations

    instances of the word "and" used to connect ideas or phrases

    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
     ultimately
    -0.07
    ornado
    -0.06
    Transactional
    -0.06
    izz
    -0.06
     otherwise
    -0.06
    ulfilled
    -0.06
    ec
    -0.06
    cf
    -0.06
    orsk
    -0.06
    527
    -0.05
    POSITIVE LOGITS
    abay
    0.08
     unlike
    0.07
    etti
    0.07
    linger
    0.07
     ún
    0.07
    -boy
    0.07
    apture
    0.07
     nó
    0.07
     boy
    0.06
    Uvs
    0.06
    Activations Density 0.040%

    No Known Activations