© 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. 17-LLAMASCOPE-RES-131K
    11. 59117
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "find" and its variations

    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
    amps
    -0.08
    /from
    -0.08
    undos
    -0.07
    cai
    -0.07
    /on
    -0.07
    ILLE
    -0.07
    ÙĪÙĨد
    -0.06
    nÄĽ
    -0.06
    ufen
    -0.06
    undi
    -0.06
    POSITIVE LOGITS
    ered
    0.11
     kiếm
    0.10
    amental
    0.10
    DOMNode
    0.10
    lay
    0.09
    ational
    0.09
    amentals
    0.09
     ways
    0.09
    NavController
    0.08
    ling
    0.08
    Activations Density 0.077%

    No Known Activations