© 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. 17-LLAMASCOPE-RES-131K
    11. 105827
    Prev
    Next
    INDEX
    Explanations

    references to cabinets or similar storage units

    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
    uncio
    -0.07
    Tank
    -0.07
    fld
    -0.07
    adh
    -0.07
    obic
    -0.07
    enn
    -0.07
    ument
    -0.07
    Ä©a
    -0.07
    sword
    -0.07
    ohl
    -0.07
    POSITIVE LOGITS
    éĸĢ
    0.10
     doors
    0.09
    ted
    0.08
     Doors
    0.08
    .gdx
    0.08
    ropic
    0.07
    -door
    0.07
     door
    0.07
    éŨ
    0.07
    maid
    0.07
    Activations Density 0.006%

    No Known Activations