© 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. 28809
    Prev
    Next
    INDEX
    Explanations

    votes and outcomes related to judicial decisions or cases

    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
    osate
    -0.07
    tober
    -0.07
     spin
    -0.07
    vatel
    -0.07
    ç«ĭãģ¦
    -0.06
    PARATOR
    -0.06
    uada
    -0.06
    rawl
    -0.06
    姿
    -0.06
    artner
    -0.06
    POSITIVE LOGITS
    RB
    0.06
     ÑģпÑĢав
    0.06
    ick
    0.06
    Tp
    0.06
     import
    0.06
    μÏĮ
    0.06
    Ỽi
    0.06
    pon
    0.05
    ¯u
    0.05
     prag
    0.05
    Activations Density 0.024%

    No Known Activations