© 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. 29582
    Prev
    Next
    INDEX
    Explanations

    file paths or URLs in the text

    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
     Rath
    -0.07
     Alt
    -0.06
    zell
    -0.06
    baum
    -0.06
    portun
    -0.06
    ushman
    -0.05
    ATER
    -0.05
    orton
    -0.05
     army
    -0.05
    zelf
    -0.05
    POSITIVE LOGITS
    νή
    0.08
    عاÙĦ
    0.07
    λεκ
    0.07
    .IContainer
    0.07
    ëį°ìĿ´íĬ¸
    0.07
    _AUX
    0.07
     Cousins
    0.07
    inalg
    0.07
    iddet
    0.07
    าà¸ĩ
    0.07
    Activations Density 0.000%

    No Known Activations