© 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. 9-LLAMASCOPE-RES-131K
    11. 98375
    Prev
    Next
    INDEX
    Explanations

    user and profile links from social media platforms

    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
    ewan
    -0.07
    obel
    -0.06
     Sheldon
    -0.06
     пÑĢок
    -0.06
    ibus
    -0.06
    ynth
    -0.06
    Gram
    -0.06
    าà¸ļ
    -0.06
    æ´ĭ
    -0.06
    CRY
    -0.06
    POSITIVE LOGITS
    -tip
    0.08
    ptions
    0.07
     Dawson
    0.06
    ozilla
    0.06
    viso
    0.06
    Äł
    0.06
    onomy
    0.06
    ¥IJ
    0.06
    akin
    0.06
    sted
    0.06
    Activations Density 0.000%

    No Known Activations