© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 82651
    Prev
    Next
    INDEX
    Explanations

    HTML comment tags and related syntax

    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
    νη
    -0.06
    illard
    -0.06
    Ïģαβ
    -0.06
     Mann
    -0.06
    icle
    -0.06
    azen
    -0.06
    UIL
    -0.06
    heel
    -0.06
    atham
    -0.06
     Hath
    -0.05
    POSITIVE LOGITS
    .gs
    0.07
    ordova
    0.07
     Barb
    0.07
    imest
    0.07
     hala
    0.07
    ervas
    0.07
    ipsis
    0.06
    lava
    0.06
    /REC
    0.06
    tur
    0.06
    Activations Density 0.004%

    No Known Activations