© 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. 88260
    Prev
    Next
    INDEX
    Explanations

    names of people or locations associated with significant events or places

    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
    erton
    -0.07
    fak
    -0.06
    ocos
    -0.06
    ãĥ¼ãĥĢ
    -0.06
    arius
    -0.06
    izon
    -0.06
    èĤĥ
    -0.06
    alone
    -0.06
    364
    -0.06
    phin
    -0.06
    POSITIVE LOGITS
     Memorial
    0.09
    ienne
    0.09
    -era
    0.09
     Cent
    0.07
    iana
    0.07
    launcher
    0.07
    utzer
    0.07
    éĻµ
    0.07
     memorial
    0.07
    ův
    0.07
    Activations Density 0.052%

    No Known Activations