© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 59075
    Prev
    Next
    INDEX
    Explanations

    references to individuals or specific groups of people within a societal context

    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
    ichten
    -0.06
    noch
    -0.06
    axies
    -0.06
    ب
    -0.06
    eras
    -0.06
    ziel
    -0.06
    ts
    -0.06
    tx
    -0.06
    akens
    -0.06
    engin
    -0.06
    POSITIVE LOGITS
    's
    0.10
    ’s
    0.08
    '
    0.07
    pecific
    0.07
    '/
    0.07
    RIPT
    0.07
    'nun
    0.07
    'nin
    0.07
    èĩªèº«
    0.07
    UTTON
    0.07
    Activations Density 0.055%

    No Known Activations