Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43740
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols typically used in mathematical or technical contexts

    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
    èĻ«
    -0.08
    éĢļãĤĬ
    -0.07
    çĻ
    -0.07
    ANJI
    -0.07
    olio
    -0.07
     kriz
    -0.07
    алÑİ
    -0.07
    QRS
    -0.07
    HEEL
    -0.07
    bero
    -0.06
    POSITIVE LOGITS
     retention
    0.12
     foam
    0.10
     lace
    0.10
     fo
    0.10
     dissip
    0.10
     fiz
    0.10
     sud
    0.09
     lasting
    0.09
     bubb
    0.09
     fro
    0.09
    Activations Density 0.003%

    No Known Activations