© 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. 128893
    Prev
    Next
    INDEX
    Explanations

    instances of the word "find" along with advice or suggestions

    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
    á»ī
    -0.07
    oved
    -0.06
    tec
    -0.06
    OPTIONS
    -0.06
    mium
    -0.06
    ldr
    -0.06
    ellery
    -0.06
    blers
    -0.06
    orch
    -0.06
     Zaman
    -0.06
    POSITIVE LOGITS
     somew
    0.09
    DOMNode
    0.08
     ways
    0.08
     somehow
    0.07
    AREST
    0.07
     onLoad
    0.07
    bor
    0.07
     Obr
    0.07
    agine
    0.07
    NavController
    0.07
    Activations Density 0.017%

    No Known Activations