© 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. 5-LLAMASCOPE-RES-131K
    11. 125841
    Prev
    Next
    INDEX
    Explanations

    references to shells and shellfish

    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
    ess
    -0.07
    esseract
    -0.07
    opia
    -0.06
    ltra
    -0.06
    ernel
    -0.06
    /control
    -0.06
    piration
    -0.06
    ernals
    -0.06
    /Instruction
    -0.06
     عÙħÙĦÛĮ
    -0.06
    POSITIVE LOGITS
    -shell
    0.08
    fish
    0.07
    iminal
    0.07
    OCK
    0.07
    INESS
    0.06
    mates
    0.06
    ipt
    0.06
    ÑĥзÑĭ
    0.06
    ieu
    0.06
    iect
    0.06
    Activations Density 0.008%

    No Known Activations