© 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 EvalsExportsinterp-engineNEWAPI 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. 2111
    Prev
    Next
    INDEX
    Explanations

    instructions related to cooking or food preparation

    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
    anda
    -0.06
    رسÛĮ
    -0.06
    åĿĢ
    -0.06
    rary
    -0.06
    rend
    -0.06
    unde
    -0.06
    erable
    -0.06
    aida
    -0.06
     vain
    -0.05
    ous
    -0.05
    POSITIVE LOGITS
    ãĤ¤ãĥ¤
    0.07
     INLINE
    0.07
    >Main
    0.07
    Ø¢Ùħ
    0.07
    IVATE
    0.07
    anni
    0.07
    инкÑĥ
    0.07
     indicated
    0.07
    _hd
    0.07
     supplied
    0.06
    Activations Density 0.034%

    No Known Activations