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

    Neuronpedia

    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. 9-LLAMASCOPE-RES-131K
    11. 95869
    Prev
    Next
    INDEX
    Explanations

    instances of specific placements or orientations of objects in a visual context

    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
    ariat
    -0.06
     MASK
    -0.06
    ady
    -0.06
    795
    -0.06
     Cass
    -0.06
    ormal
    -0.05
     Void
    -0.05
    ä½ķãģĭ
    -0.05
    USD
    -0.05
    ka
    -0.05
    POSITIVE LOGITS
    bildung
    0.07
     MetroFramework
    0.07
    IMIT
    0.07
    lename
    0.06
    utters
    0.06
    ilere
    0.06
    YLES
    0.06
    elts
    0.06
    á»ķi
    0.06
    esson
    0.06
    Activations Density 0.028%

    No Known Activations