© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 7-LLAMASCOPE-RES-32K
    11. 5292
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming structure and visibility qualifiers in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģķãĤī
    -0.18
    ãģ¾ãģŁ
    -0.15
    NotSupportedException
    -0.15
    yal
    -0.14
    TXT
    -0.14
    alg
    -0.14
    ISS
    -0.14
    تÙģ
    -0.14
     Warehouse
    -0.13
    ائر
    -0.13
    POSITIVE LOGITS
     credit
    0.16
     smear
    0.15
    cmb
    0.15
    PAD
    0.15
    HEMA
    0.15
    ABI
    0.14
    jom
    0.14
    credit
    0.14
    .mdl
    0.14
    ám
    0.14
    Activations Density 0.003%

    No Known Activations