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. 43663
    Prev
    Next
    INDEX
    Explanations

    references to historical events, particularly those involving significant societal or political changes

    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
    geber
    -0.07
    532
    -0.07
    опÑĢи
    -0.07
    24
    -0.07
    201
    -0.07
    /Dk
    -0.07
    abcdefghijklmnop
    -0.06
    ãĥ¥
    -0.06
    22
    -0.06
    :\/\/
    -0.06
    POSITIVE LOGITS
    s
    0.35
    年代
    0.20
    ies
    0.18
    ties
    0.17
    's
    0.17
    sWith
    0.15
    sand
    0.14
    S
    0.14
    ’s
    0.14
    ths
    0.13
    Activations Density 0.028%

    No Known Activations