© 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. 82926
    Prev
    Next
    INDEX
    Explanations

    references to academic journals and their related metadata

    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
     Lodge
    -0.07
    erton
    -0.06
    neau
    -0.06
    ãĥ¼ãĥ«ãĥī
    -0.06
    anced
    -0.06
    Ñĥда
    -0.06
    <Void
    -0.06
    SEX
    -0.06
     unf
    -0.06
    wk
    -0.06
    POSITIVE LOGITS
    ogy
    0.07
    Pid
    0.06
    ObjectContext
    0.06
    ovat
    0.06
    atatype
    0.06
    UBY
    0.06
    óst
    0.06
    rical
    0.06
    cko
    0.06
    STACK
    0.06
    Activations Density 0.001%

    No Known Activations