© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 3923
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Hanover" and its variations in context

    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
    éŃĤ
    -0.08
    #
    -0.08
    ysi
    -0.08
    acente
    -0.08
    ãĥ¥
    -0.08
    ]={↵
    -0.07
    иÑĨин
    -0.07
    ymm
    -0.07
     voks
    -0.07
    Ñĩики
    -0.07
    POSITIVE LOGITS
     Lect
    0.09
    lect
    0.08
     Rising
    0.06
     lect
    0.06
     Singleton
    0.06
     Ves
    0.06
     sandwich
    0.06
    LECT
    0.06
    lope
    0.06
     vital
    0.05
    Activations Density 0.001%

    No Known Activations