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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 103839
    Prev
    Next
    INDEX
    Explanations

    C programming language header files and data type definitions

    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
    emean
    -0.08
    andest
    -0.08
    anja
    -0.07
    eki
    -0.07
    alten
    -0.07
     Jaune
    -0.07
    å§Ķ
    -0.07
    anje
    -0.07
    #
    -0.07
    âĸį
    -0.07
    POSITIVE LOGITS
     Holden
    0.06
    cents
    0.06
    ONA
    0.06
    LS
    0.06
    bk
    0.06
    tb
    0.05
    sp
    0.05
    ls
    0.05
    _extensions
    0.05
    ONEY
    0.05
    Activations Density 0.001%

    No Known Activations