© 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. 9-LLAMASCOPE-RES-32K
    6. 980
    Prev
    Next
    INDEX
    Explanations

    keywords related to structure, organization, and function within an institutional context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    лей
    -0.13
    .reporting
    -0.13
    ACP
    -0.13
    омеÑĤ
    -0.13
    canf
    -0.13
    å®¶çļĦ
    -0.13
    onya
    -0.13
    лÑıв
    -0.13
    اش
    -0.13
     Permit
    -0.13
    POSITIVE LOGITS
     Muk
    0.16
    lik
    0.14
    urance
    0.14
    .createQuery
    0.14
    avit
    0.14
    erals
    0.13
    Ear
    0.13
     modern
    0.13
    obl
    0.13
    arto
    0.12
    Activations Density 0.016%

    No Known Activations