© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95773
    Prev
    Next
    INDEX
    Explanations

    references to body parts and physical proximity

    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
     eyed
    -0.08
    pany
    -0.07
    roupe
    -0.07
    umbledore
    -0.07
    eut
    -0.07
    заб
    -0.07
    ÑĥÑĢн
    -0.07
    egov
    -0.07
    brero
    -0.07
     nghiá»ĩp
    -0.06
    POSITIVE LOGITS
    sters
    0.06
    adel
    0.06
    olas
    0.06
    -mounted
    0.06
    enth
    0.06
    nic
    0.05
     fel
    0.05
    еÑģÑĤи
    0.05
    /trunk
    0.05
    alam
    0.05
    Activations Density 0.003%

    No Known Activations