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. 43849
    Prev
    Next
    INDEX
    Explanations

    references to data theft and personal information publication laws

    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
    erif
    -0.06
    esch
    -0.06
    ittel
    -0.06
    .FontStyle
    -0.05
     ÐĦв
    -0.05
    roller
    -0.05
    _abstract
    -0.05
    лÑĥг
    -0.05
    connector
    -0.05
     ÑĤÑĢанÑģпоÑĢÑĤ
    -0.05
    POSITIVE LOGITS
     revenge
    0.14
     Revenge
    0.14
     sext
    0.13
     nude
    0.11
     Nude
    0.10
     intimate
    0.10
     photos
    0.10
     images
    0.10
     explicit
    0.10
     distribution
    0.09
    Activations Density 0.013%

    No Known Activations