© 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. 16749
    Prev
    Next
    INDEX
    Explanations

    references to parent and child relationships in document structure

    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
    upertino
    -0.09
    deaux
    -0.09
    .IsNullOr
    -0.09
    ramework
    -0.09
     AsyncCallback
    -0.09
    WithPath
    -0.09
    дн
    -0.09
    _framework
    -0.09
    ubi
    -0.09
    lix
    -0.08
    POSITIVE LOGITS
     d
    0.07
     Ultra
    0.07
    at
    0.07
     ultra
    0.06
    el
    0.06
     cl
    0.06
     Ef
    0.06
     Morr
    0.06
     (
    0.06
     Ele
    0.06
    Activations Density 0.002%

    No Known Activations