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

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 61472
    Prev
    Next
    INDEX
    Explanations

    mentions of power-related concepts or themes

    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
    orsi
    -0.07
    .osgi
    -0.07
    ont
    -0.07
    lient
    -0.07
    onn
    -0.07
    achuset
    -0.07
    ongan
    -0.07
    abin
    -0.07
    onto
    -0.07
    hythm
    -0.07
    POSITIVE LOGITS
    ose
    0.09
    ̣
    0.06
    ip
    0.06
    ey
    0.06
    ullan
    0.06
    embr
    0.06
    uro
    0.06
    imore
    0.06
    áºł
    0.06
    oda
    0.06
    Activations Density 0.169%

    No Known Activations