© 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. 17-LLAMASCOPE-RES-131K
    6. 128441
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names associated with various entities and organizations

    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
     باش
    -0.08
    ư
    -0.07
    ickey
    -0.07
    olini
    -0.07
    elves
    -0.07
    елиÑĩ
    -0.07
     provoz
    -0.07
    phia
    -0.07
    ếu
    -0.07
    елов
    -0.07
    POSITIVE LOGITS
     fame
    0.16
     Fame
    0.10
     whom
    0.10
     who
    0.09
    who
    0.06
    877
    0.06
     tents
    0.06
     lim
    0.06
    206
    0.06
     ret
    0.06
    Activations Density 0.031%

    No Known Activations