Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 106166
    Prev
    Next
    INDEX
    Explanations

    references to feelings of discomfort or unease

    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
     liberal
    -0.06
    izable
    -0.06
    IZED
    -0.06
     Charm
    -0.06
    stadt
    -0.06
    acting
    -0.06
    emouth
    -0.06
    eyer
    -0.06
    atorial
    -0.06
     ìĭł
    -0.06
    POSITIVE LOGITS
    ingly
    0.10
    iquid
    0.08
    axed
    0.08
    /free
    0.07
    owy
    0.07
    ardin
    0.07
     ByteArray
    0.07
    inki
    0.07
    ace
    0.07
    inks
    0.07
    Activations Density 0.004%

    No Known Activations