© 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. 9-LLAMASCOPE-RES-131K
    6. 95908
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names and 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
    krom
    -0.08
    phis
    -0.07
    imb
    -0.06
    oe
    -0.06
    APS
    -0.06
    aps
    -0.06
    DMI
    -0.06
    ä¿Ĺ
    -0.06
    erset
    -0.06
    htag
    -0.06
    POSITIVE LOGITS
    LLU
    0.08
     itself
    0.07
    uiltin
    0.07
    İS
    0.07
    гоÑĢ
    0.06
    enschaft
    0.06
     Gors
    0.06
     Jenner
    0.06
    ollipop
    0.06
    iolet
    0.06
    Activations Density 0.002%

    No Known Activations