© 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. 78681
    Prev
    Next
    INDEX
    Explanations

    topics related to crime and societal issues

    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
    eco
    -0.06
     desp
    -0.06
     ad
    -0.06
    oice
    -0.06
     sep
    -0.06
    agini
    -0.05
     Pend
    -0.05
    ายà¸Ļ
    -0.05
    âĨ
    -0.05
     ap
    -0.05
    POSITIVE LOGITS
     motive
    0.08
    æĬ¥
    0.07
    mdir
    0.07
    моÑĤ
    0.07
    oley
    0.07
    -pills
    0.07
    .scalablytyped
    0.07
    elastic
    0.06
    RuleContext
    0.06
    åħ¬éĸĭ
    0.06
    Activations Density 0.003%

    No Known Activations