© 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. 71452
    Prev
    Next
    INDEX
    Explanations

    descriptions of challenging and frustrating tasks

    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
    hen
    -0.07
    atat
    -0.06
    Ñĩенко
    -0.06
     import
    -0.06
     clap
    -0.06
    horse
    -0.06
     vant
    -0.06
    ollen
    -0.06
    ocommerce
    -0.06
    525
    -0.06
    POSITIVE LOGITS
    вод
    0.06
    MBED
    0.06
     conn
    0.06
    ëŁī
    0.06
     Locker
    0.06
    elters
    0.06
     ÑĤÑĢанÑģп
    0.06
    mrt
    0.06
    ohl
    0.06
    ilik
    0.06
    Activations Density 0.010%

    No Known Activations