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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-32K
    11. 15392
    Prev
    Next
    INDEX
    Explanations

    references to technical or programming concepts

    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
    ůl
    -0.13
    lyph
    -0.13
    pees
    -0.13
    ãģªãģĮ
    -0.13
    usercontent
    -0.13
    ghan
    -0.13
    lý
    -0.13
    INFRINGEMENT
    -0.12
    ÃħŸ
    -0.12
    ụp
    -0.12
    POSITIVE LOGITS
     éĺ
    0.15
    |M
    0.13
    edException
    0.13
    —or
    0.12
    ÑģÑĤоÑĢ
    0.12
    TabIndex
    0.12
    —if
    0.12
    "":
    0.12
    ï¼Ł↵↵
    0.12
    $_
    0.12
    Activations Density 3.851%

    No Known Activations