© 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. 16931
    Prev
    Next
    INDEX
    Explanations

    references to literacy and educational programs

    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
     Tits
    -0.08
    iddy
    -0.07
    çĺ
    -0.07
    çīĮ
    -0.07
    ichern
    -0.07
     Peach
    -0.07
    ãĤ¤ãĥ³ãĥĪ
    -0.07
    zem
    -0.07
    _shuffle
    -0.07
     Dorm
    -0.07
    POSITIVE LOGITS
     Development
    0.07
     developmental
    0.07
     early
    0.07
     development
    0.07
     intervention
    0.06
     intervened
    0.06
     Intelligence
    0.06
    OME
    0.06
    isc
    0.06
     Early
    0.06
    Activations Density 0.043%

    No Known Activations