© 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 EvalsExportsAPI 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. 3516
    Prev
    Next
    INDEX
    Explanations

    spatial relationships and positional descriptions

    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
    pez
    -0.07
    etto
    -0.07
    tery
    -0.07
    gia
    -0.06
    .readString
    -0.06
    .setScene
    -0.06
    Ế
    -0.06
     surrounding
    -0.06
    .djangoproject
    -0.06
    erno
    -0.06
    POSITIVE LOGITS
     distant
    0.18
    éģł
    0.15
    è¿ľ
    0.14
     far
    0.14
    far
    0.14
     remote
    0.13
    remote
    0.12
     remot
    0.12
     Far
    0.11
    Far
    0.11
    Activations Density 0.112%

    No Known Activations