© 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. 83495
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific names within a context

    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
    avern
    -0.07
    orsche
    -0.06
    .SP
    -0.06
    otos
    -0.06
    aniel
    -0.06
    uma
    -0.06
     slack
    -0.06
    orno
    -0.06
    ÑĶн
    -0.06
    oze
    -0.05
    POSITIVE LOGITS
    cies
    0.08
    .gdx
    0.07
    erif
    0.07
    çĽ
    0.07
     moden
    0.06
    -Sah
    0.06
    oland
    0.06
    ubbo
    0.06
    Bonus
    0.06
    _firestore
    0.06
    Activations Density 0.057%

    No Known Activations