© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 5-LLAMASCOPE-RES-131K
    11. 125835
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific identifiers related to notable individuals, films, and potentially significant events

    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
    ullet
    -0.07
    abet
    -0.07
    kate
    -0.07
    κή
    -0.07
    ariat
    -0.07
    722
    -0.07
    fak
    -0.06
     SPDX
    -0.06
    linger
    -0.06
     Baldwin
    -0.06
    POSITIVE LOGITS
     Perr
    0.07
    naments
    0.06
    err
    0.06
    ulos
    0.06
    usted
    0.05
     ro
    0.05
    éĮ
    0.05
     vis
    0.05
    olon
    0.05
    usa
    0.05
    Activations Density 0.005%

    No Known Activations