© 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. 77032
    Prev
    Next
    INDEX
    Explanations

    instances of the word "call" and its variations

    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
    esa
    -0.08
    eder
    -0.07
    оÑı
    -0.06
    strap
    -0.06
    arro
    -0.06
    ãĥ¼ãĥĢ
    -0.06
    iÄĩ
    -0.06
    atk
    -0.06
    stdarg
    -0.06
     manual
    -0.06
    POSITIVE LOGITS
     attention
    0.10
     dib
    0.10
    oused
    0.09
    /text
    0.09
    ously
    0.08
    attention
    0.07
     upon
    0.07
    ibrate
    0.07
    igraphy
    0.07
     quits
    0.07
    Activations Density 0.017%

    No Known Activations