© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 3764
    Prev
    Next
    INDEX
    Explanations

    references to legal and administrative details related to law offices

    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
     ct
    -0.06
    302
    -0.06
     Lafayette
    -0.06
     recep
    -0.06
     -
    -0.06
    pare
    -0.06
    891
    -0.05
     Hear
    -0.05
    -0.05
    422
    -0.05
    POSITIVE LOGITS
    ABL
    0.08
    edir
    0.07
    omanip
    0.07
    ebek
    0.07
    ستاÙĨ
    0.07
    bew
    0.07
    liÄį
    0.07
    istence
    0.07
    ارج
    0.07
    xde
    0.07
    Activations Density 0.001%

    No Known Activations