Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96212
    Prev
    Next
    INDEX
    Explanations

    terms related to taxation and financial duties

    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
    toa
    -0.06
    åħ
    -0.05
     subsid
    -0.05
    stances
    -0.05
     Traverse
    -0.05
     Petit
    -0.05
     shade
    -0.05
     Benn
    -0.05
     Hue
    -0.05
     coun
    -0.05
    POSITIVE LOGITS
    ookie
    0.08
    znik
    0.08
    iram
    0.07
    éro
    0.07
    BOSE
    0.07
    $LANG
    0.07
    daq
    0.07
     Colleg
    0.07
     keycode
    0.07
    erno
    0.07
    Activations Density 0.001%

    No Known Activations