© 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. 15-LLAMASCOPE-RES-131K
    11. 90442
    Prev
    Next
    INDEX
    Explanations

    statements of confession or claims related to legal proceedings

    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
    agina
    -0.09
    uzzi
    -0.09
    ãĥ«ãĥĪ
    -0.09
    irá
    -0.09
    าà¸ķรà¸IJาà¸Ļ
    -0.08
    ä¸ŃæĸĩåŃĹå¹ķ
    -0.08
     GLfloat
    -0.08
     merak
    -0.08
    rysler
    -0.08
    enia
    -0.08
    POSITIVE LOGITS
    ced
    0.07
     himself
    0.06
     had
    0.06
    èµ·
    0.06
     prior
    0.06
     @
    0.05
     et
    0.05
     was
    0.05
    0.05
     du
    0.05
    Activations Density 0.026%

    No Known Activations