© 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. 15-LLAMASCOPE-RES-131K
    11. 88476
    Prev
    Next
    INDEX
    Explanations

    references to the color gray or variations of it

    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
    aire
    -0.07
    use
    -0.07
     пÑĢо
    -0.06
    ekt
    -0.06
    uent
    -0.06
    aclass
    -0.06
    KER
    -0.06
    ãģĤãģ£ãģŁ
    -0.06
    azer
    -0.06
    ptic
    -0.06
    POSITIVE LOGITS
    hound
    0.10
    ening
    0.08
    enstein
    0.08
    anke
    0.07
    elper
    0.07
    ened
    0.07
     Sang
    0.07
    inke
    0.07
    ccione
    0.07
    enheim
    0.07
    Activations Density 0.022%

    No Known Activations