© 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. 84349
    Prev
    Next
    INDEX
    Explanations

    terms that describe discomfort or irritation

    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
    lify
    -0.08
    erif
    -0.08
    odzi
    -0.08
     Luz
    -0.07
    uitka
    -0.07
    inka
    -0.07
    lake
    -0.07
    stral
    -0.07
    çĬ¯ç½ª
    -0.07
    _FLUSH
    -0.06
    POSITIVE LOGITS
    ingly
    0.10
    ancel
    0.08
    antal
    0.07
    ulence
    0.07
    ants
    0.06
    .opensource
    0.06
    ative
    0.06
    xe
    0.06
    ours
    0.06
    OptionsMenu
    0.06
    Activations Density 0.005%

    No Known Activations