© 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. 11-LLAMASCOPE-RES-32K
    6. 7129
    Prev
    Next
    INDEX
    Explanations

    abbreviations, acronyms, and references to various organizations and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enance
    -0.14
    ambre
    -0.14
    atta
    -0.14
    inkle
    -0.14
    ogne
    -0.14
    avn
    -0.14
    508
    -0.13
    eyn
    -0.13
    ateg
    -0.13
    Nation
    -0.13
    POSITIVE LOGITS
    dda
    0.14
    ÏĢη
    0.13
    ossip
    0.13
    عار
    0.13
     Dann
    0.13
     ãĤ¢ãĤ¤
    0.13
    ÙıÙĪÙĨ
    0.13
    Ø®ÙĪ
    0.13
     Bek
    0.12
    дÑı
    0.12
    Activations Density 0.334%

    No Known Activations