© 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. 85779
    Prev
    Next
    INDEX
    Explanations

    physical features and characteristics of objects or spaces

    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
    ogle
    -0.07
    adb
    -0.07
    Bounding
    -0.07
    ÑĪи
    -0.06
    estr
    -0.06
    pz
    -0.06
    Registrar
    -0.06
    íĭ´
    -0.06
     Holl
    -0.06
    ãĥ³ãĤ¬
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.07
    åıĬ
    0.07
     OTHERWISE
    0.07
    jis
    0.06
    åĽ½åĨħ
    0.06
    áte
    0.06
    ]bool
    0.06
    aday
    0.06
    alis
    0.06
    ertino
    0.06
    Activations Density 0.036%

    No Known Activations