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. 96017
    Prev
    Next
    INDEX
    Explanations

    references to demographics and economic data

    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
    ieu
    -0.06
    fir
    -0.06
    ãĥĵãĥ¼
    -0.06
    efon
    -0.06
    poz
    -0.06
    pz
    -0.06
    lev
    -0.06
    acket
    -0.06
    ormal
    -0.06
    ogene
    -0.05
    POSITIVE LOGITS
    omor
    0.07
     Shelf
    0.07
    population
    0.07
     inval
    0.07
     voks
    0.07
     nüfus
    0.06
    Ñıж
    0.06
    .LoadScene
    0.06
    _population
    0.06
    Å©
    0.06
    Activations Density 0.235%

    No Known Activations