© 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. 55938
    Prev
    Next
    INDEX
    Explanations

    references to web links or permalink structures

    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
    ange
    -0.08
    assen
    -0.07
    aptor
    -0.07
    agle
    -0.07
    aldi
    -0.07
    ãĤ¹ãĤ«
    -0.07
    ung
    -0.06
    emin
    -0.06
    зÑĮ
    -0.06
    elle
    -0.06
    POSITIVE LOGITS
    #
    0.07
    _ASSUME
    0.06
    foy
    0.06
     Gat
    0.06
    RegularExpression
    0.06
     foe
    0.06
    ãĥĨãĥ«
    0.06
     infusion
    0.06
    ůl
    0.06
    اءات
    0.06
    Activations Density 0.001%

    No Known Activations