© 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. 29116
    Prev
    Next
    INDEX
    Explanations

    structured items or references, particularly related to time and data formats

    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
    inx
    -0.07
    ichni
    -0.06
    herits
    -0.06
    acje
    -0.06
    owie
    -0.06
    rieving
    -0.06
    cht
    -0.06
    rai
    -0.06
    ominator
    -0.06
    erts
    -0.06
    POSITIVE LOGITS
     stru
    0.06
    RuleContext
    0.06
     hoạch
    0.06
    umb
    0.06
    -prev
    0.06
    ÙIJÙĩ
    0.06
    EMA
    0.06
    _DH
    0.06
     cameo
    0.06
     neur
    0.06
    Activations Density 0.000%

    No Known Activations