© 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. 88446
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing anticipation or follow-up information

    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
    óz
    -0.07
    align
    -0.06
    hur
    -0.06
    ansen
    -0.06
    stad
    -0.06
    is
    -0.06
    kin
    -0.06
     beden
    -0.06
    pd
    -0.06
    ion
    -0.06
    POSITIVE LOGITS
     for
    0.08
    ysis
    0.07
    ABCDEFGHIJKLMNOP
    0.07
    аÑĢа
    0.07
    NTAX
    0.07
    631
    0.07
    -urlencoded
    0.07
    ary
    0.07
    ÑĢаÑī
    0.07
    740
    0.07
    Activations Density 0.003%

    No Known Activations