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

    Neuronpedia

    Jacobian LensNEW
    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. 96548
    Prev
    Next
    INDEX
    Explanations

    food-related items and meals

    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
    -0.06
     powerful
    -0.06
    -
    -0.06
    ↵
    -0.06
     official
    -0.06
     I
    -0.06
     Tom
    -0.05
     Powerful
    -0.05
     am
    -0.05
     Z
    -0.05
    POSITIVE LOGITS
    anzeigen
    0.09
    urette
    0.09
    afone
    0.08
    ewan
    0.08
    /stretch
    0.08
    çĴ
    0.08
    iyel
    0.08
     çĬ
    0.08
    $MESS
    0.08
    OKIE
    0.08
    Activations Density 0.053%

    No Known Activations