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. 19-LLAMASCOPE-RES-32K
    6. 6313
    Prev
    Next
    INDEX
    Explanations

    information and terms related to data organization and academic qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obo
    -0.17
    AZY
    -0.15
    ients
    -0.14
    []){↵
    -0.14
    entifier
    -0.14
    ones
    -0.14
    ysqli
    -0.14
    ï¼īï¼ļ
    -0.13
    asto
    -0.13
    .addComponent
    -0.13
    POSITIVE LOGITS
    :
    0.36
     =
    0.25
    =
    0.20
    yles
    0.17
     OK
    0.16
     same
    0.15
    ensburg
    0.15
    ï¼ļ
    0.14
     unknown
    0.14
     sama
    0.14
    Activations Density 0.180%

    No Known Activations