© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 41374
    Prev
    Next
    INDEX
    Explanations

    references to transportation and access to locations

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    istan
    -0.06
     Hamp
    -0.06
    raki
    -0.06
    ropoda
    -0.06
    gesch
    -0.06
     terrace
    -0.06
    anche
    -0.05
     Gonz
    -0.05
     ç¨
    -0.05
    .sap
    -0.05
    POSITIVE LOGITS
     parking
    0.13
    Parking
    0.12
     Parking
    0.11
     parked
    0.08
    åħ¥åı£
    0.08
     ranger
    0.08
    /maps
    0.08
    .getStart
    0.07
     entrance
    0.07
    .broadcast
    0.07
    Activations Density 0.018%

    No Known Activations