© 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. 96324
    Prev
    Next
    INDEX
    Explanations

    activities related to physical actions or changes

    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
    aron
    -0.08
    inned
    -0.08
     pulumi
    -0.07
    ceae
    -0.07
    cation
    -0.06
    andon
    -0.06
    hape
    -0.06
    175
    -0.06
    pected
    -0.06
    anca
    -0.06
    POSITIVE LOGITS
     Yer
    0.06
    ednou
    0.06
     Harding
    0.06
     Far
    0.06
    erosis
    0.06
    kaz
    0.06
    cott
    0.06
    ABEL
    0.06
     Bout
    0.06
    GameData
    0.06
    Activations Density 0.072%

    No Known Activations