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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 118441
    Prev
    Next
    INDEX
    Explanations

    personal experiences 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
    azzo
    -0.07
    lisi
    -0.07
     noqa
    -0.07
    IGHL
    -0.07
    icles
    -0.06
    oyo
    -0.06
    łģ
    -0.06
    adamente
    -0.06
    coni
    -0.06
    ssid
    -0.06
    POSITIVE LOGITS
    defs
    0.07
     om
    0.07
    ãĢijãĢIJ
    0.06
     instead
    0.06
    tw
    0.06
    618
    0.06
     substitute
    0.06
    heits
    0.06
    ound
    0.06
     fen
    0.06
    Activations Density 0.008%

    No Known Activations