© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 75897
    Prev
    Next
    INDEX
    Explanations

    terms related to impairment and its effects

    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
    zac
    -0.07
    nette
    -0.07
    обÑĢаÐ
    -0.07
    egative
    -0.07
    athan
    -0.07
    obby
    -0.07
    inst
    -0.07
    rut
    -0.07
    blade
    -0.07
    keh
    -0.07
    POSITIVE LOGITS
    ments
    0.11
    ment
    0.10
    mentation
    0.08
    edly
    0.07
    757
    0.07
    MENTS
    0.07
    mented
    0.07
    243
    0.07
    oen
    0.07
    ing
    0.06
    Activations Density 0.024%

    No Known Activations