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. 18-LLAMASCOPE-RES-32K
    6. 28799
    Prev
    Next
    INDEX
    Explanations

    names and titles associated with individuals in the educational field, particularly superintendents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Spokane
    -0.20
     Disneyland
    -0.18
     Sask
    -0.18
     BYU
    -0.16
     Manitoba
    -0.16
     dilig
    -0.16
    ogne
    -0.16
     Tasmania
    -0.16
    okane
    -0.15
     Fresno
    -0.15
    POSITIVE LOGITS
     Miami
    0.57
    Miami
    0.52
     Florida
    0.40
    Florida
    0.36
    iami
    0.30
     Cuban
    0.30
     Saras
    0.29
     Marlins
    0.28
     Coconut
    0.28
     Bahamas
    0.28
    Activations Density 0.149%

    No Known Activations