Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 10-LLAMASCOPE-RES-32K
    6. 23291
    Prev
    Next
    INDEX
    Explanations

    references to bans, prohibitions, and restrictions on various activities or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sublicense
    -0.15
    cul
    -0.15
    enha
    -0.14
    aggi
    -0.14
     NC
    -0.14
    206
    -0.14
    enz
    -0.14
    èĤ©
    -0.13
    ÛĮات
    -0.13
    upe
    -0.13
    POSITIVE LOGITS
    ishment
    0.17
    quet
    0.15
    quets
    0.15
    stellen
    0.14
    dden
    0.14
    LOUR
    0.14
    лÑĸд
    0.14
     sing
    0.14
    hammer
    0.14
    chwitz
    0.14
    Activations Density 0.053%

    No Known Activations