© 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. 61916
    Prev
    Next
    INDEX
    Explanations

    terms related to financial status and net worth

    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
     excess
    -0.06
     converts
    -0.06
     Spin
    -0.06
     Kl
    -0.05
     Batt
    -0.05
    临
    -0.05
    624
    -0.05
    erce
    -0.05
    ncy
    -0.05
     Valentine
    -0.05
    POSITIVE LOGITS
     semiclass
    0.07
    inand
    0.07
    Unload
    0.07
     takson
    0.07
    RTOS
    0.07
    ÏĦÎŃ
    0.07
    PostalCodes
    0.07
    SGlobal
    0.07
    SSIP
    0.07
    viously
    0.07
    Activations Density 0.000%

    No Known Activations