© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77485
    Prev
    Next
    INDEX
    Explanations

    references to Italian cinema and Italian-themed content

    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
    pler
    -0.08
    eph
    -0.08
    isser
    -0.07
    ertas
    -0.06
    _MACRO
    -0.06
    aptive
    -0.06
    EEP
    -0.06
    asic
    -0.06
    703
    -0.06
     royalties
    -0.06
    POSITIVE LOGITS
    oris
    0.07
    èĻİ
    0.07
    导
    0.07
     full
    0.07
    full
    0.06
    parm
    0.06
    rent
    0.06
     Mp
    0.06
     fullfile
    0.06
    .criteria
    0.06
    Activations Density 0.001%

    No Known Activations