© 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 EvalsExportsinterp-engineNEWAPI 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. 30505
    Prev
    Next
    INDEX
    Explanations

    negative sentiment indicators

    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
    olume
    -0.06
     заÑĤ
    -0.06
    oulouse
    -0.06
    seau
    -0.06
    hev
    -0.06
    i
    -0.06
    e
    -0.06
    m
    -0.06
     Î
    -0.06
    aus
    -0.06
    POSITIVE LOGITS
    PIO
    0.08
    obe
    0.07
    _HS
    0.07
    CSR
    0.07
    @Web
    0.07
    exc
    0.07
    &type
    0.07
    orado
    0.06
    unately
    0.06
     Ðļоли
    0.06
    Activations Density 0.031%

    No Known Activations