© 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. 30-LLAMASCOPE-RES-32K
    11. 5883
    Prev
    Next
    INDEX
    Explanations

    structured markup or syntax within programming or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orgia
    -0.17
    elho
    -0.16
    лаÑģ
    -0.15
    olland
    -0.14
     recount
    -0.14
    dup
    -0.14
    nell
    -0.14
    Ñıк
    -0.13
    âĨIJ
    -0.13
    å¢
    -0.13
    POSITIVE LOGITS
    param
    0.35
     param
    0.32
    returns
    0.28
    typeparam
    0.26
    remarks
    0.26
     returns
    0.25
    -param
    0.24
    exception
    0.24
     remarks
    0.23
     Param
    0.23
    Activations Density 0.005%

    No Known Activations