© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 86717
    Prev
    Next
    INDEX
    Explanations

    inquiries about locations or places

    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
     Rarity
    -0.07
    å¯
    -0.07
    ãģ¹ãģ¦
    -0.07
    æĤī
    -0.07
    olean
    -0.07
    resden
    -0.07
    овиÑĩ
    -0.06
    Ñĩини
    -0.06
    ÙĪÛĮÙĨ
    -0.06
    tings
    -0.06
    POSITIVE LOGITS
    ETA
    0.06
    ateg
    0.06
     Randall
    0.06
     Wald
    0.05
     promised
    0.05
    ugen
    0.05
    939
    0.05
     understanding
    0.05
    oom
    0.05
     offending
    0.05
    Activations Density 0.014%

    No Known Activations