© 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. 15-LLAMASCOPE-RES-131K
    11. 104116
    Prev
    Next
    INDEX
    Explanations

    actions and phrases related to involving children in cooking and food experimentation

    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
     видÑĥ
    -0.07
    Networking
    -0.07
    Ľå»º
    -0.07
    iddi
    -0.07
     Launcher
    -0.07
    endas
    -0.07
    Uri
    -0.07
    wang
    -0.07
    OG
    -0.07
    ple
    -0.06
    POSITIVE LOGITS
     Monroe
    0.06
     Pride
    0.06
     Junior
    0.06
     handled
    0.06
     hands
    0.06
    dest
    0.06
     Barg
    0.05
    AFE
    0.05
     taller
    0.05
     OnTrigger
    0.05
    Activations Density 0.006%

    No Known Activations