© 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. 127389
    Prev
    Next
    INDEX
    Explanations

    themes related to familial roles and responsibilities

    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
    =YES
    -0.08
    Gatt
    -0.07
    xCD
    -0.07
    ertools
    -0.07
    ÏĮδ
    -0.07
    akens
    -0.07
    ainen
    -0.07
    ozilla
    -0.07
    _Tis
    -0.07
    braco
    -0.07
    POSITIVE LOGITS
     compens
    0.06
     outward
    0.06
     offset
    0.06
    offset
    0.06
    ___
    0.06
    _offsets
    0.06
     compensated
    0.06
     Silent
    0.06
     opportunities
    0.05
     expressed
    0.05
    Activations Density 0.057%

    No Known Activations