© 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. 106140
    Prev
    Next
    INDEX
    Explanations

    references to governmental and organizational entities

    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
    776
    -0.07
    Verifier
    -0.07
    ůže
    -0.07
     ngoại
    -0.07
    AINS
    -0.07
    ians
    -0.07
    upa
    -0.06
    ÙģÙĩ
    -0.06
    ä¸Ī
    -0.06
    äºĭæĥħ
    -0.06
    POSITIVE LOGITS
    osu
    0.07
    eneg
    0.07
     release
    0.07
     said
    0.06
    enthal
    0.06
     bol
    0.06
     Fourth
    0.06
     boss
    0.06
    TECTED
    0.06
    iage
    0.06
    Activations Density 0.060%

    No Known Activations