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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-LLAMASCOPE-RES-131K
    6. 96130
    Prev
    Next
    INDEX
    Explanations

    words related to legal and financial industry roles

    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
    tÃŃ
    -0.07
    íĥģ
    -0.07
    ozÃŃ
    -0.07
    akis
    -0.07
    ovich
    -0.07
    idis
    -0.07
    ramework
    -0.07
    tür
    -0.07
    _ASSUME
    -0.07
     gsi
    -0.07
    POSITIVE LOGITS
    ิà¸ŀ
    0.06
    ISM
    0.06
    VERT
    0.05
    eden
    0.05
    uch
    0.05
    á»ĩ
    0.05
     onward
    0.05
    427
    0.05
    isto
    0.05
     Woodward
    0.05
    Activations Density 0.002%

    No Known Activations