© 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 EvalsExportsinterp-engineNEWAPI 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. 74175
    Prev
    Next
    INDEX
    Explanations

    terms and contexts related to flags and their functionality

    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
    é¦
    -0.08
    dna
    -0.07
     é¦
    -0.07
     circumcision
    -0.07
    elik
    -0.06
    avi
    -0.06
     paz
    -0.06
     tá»Ń
    -0.06
    auga
    -0.06
    377
    -0.06
    POSITIVE LOGITS
     Rules
    0.07
    Rules
    0.07
     Blasio
    0.07
    (cd
    0.06
    Rule
    0.06
     Rule
    0.06
     ê·ľ
    0.06
     Vaults
    0.06
     move
    0.06
     Move
    0.06
    Activations Density 0.001%

    No Known Activations