© 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. 40855
    Prev
    Next
    INDEX
    Explanations

    prepositions and related constructs that indicate relationships or structures within the text

    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
    'gc
    -0.12
    бÑĥдÑĮ
    -0.10
    ¶Į
    -0.09
     ç¿
    -0.09
    KHR
    -0.09
    _________________↵↵
    -0.09
    ÙĩÙĨÚ¯
    -0.09
     ðŁĺī↵↵
    -0.08
    OUCH
    -0.08
    िण
    -0.08
    POSITIVE LOGITS
    âĢ¦↵
    0.06
     pretty
    0.06
     quite
    0.06
     Sh
    0.06
     Shot
    0.06
     Sp
    0.06
     really
    0.05
    !
    0.05
    ism
    0.05
    shot
    0.05
    Activations Density 0.000%

    No Known Activations