© 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. 78708
    Prev
    Next
    INDEX
    Explanations

    mentions of family and their dynamics

    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
    Ø°
    -0.07
    ÑİÑĢ
    -0.06
     mädchen
    -0.06
     lifestyles
    -0.06
    ihu
    -0.06
    CREEN
    -0.06
    inant
    -0.06
    otel
    -0.06
    umper
    -0.06
    å¹ķ
    -0.06
    POSITIVE LOGITS
    ework
    0.08
     job
    0.07
    uar
    0.07
     doma
    0.07
    job
    0.06
     honey
    0.06
     Job
    0.06
     work
    0.06
    arken
    0.06
     business
    0.06
    Activations Density 0.069%

    No Known Activations