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. 22-LLAMASCOPE-RES-32K
    6. 28211
    Prev
    Next
    INDEX
    Explanations

    references to government funding and health services related to family planning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -UA
    -0.18
    -CN
    -0.16
    rieb
    -0.15
    ixin
    -0.15
     Bahamas
    -0.15
    orida
    -0.15
    stag
    -0.14
    .XR
    -0.14
     Cummings
    -0.14
    wp
    -0.14
    POSITIVE LOGITS
     Nebraska
    0.46
     Omaha
    0.46
    braska
    0.29
    Om
    0.28
     Neb
    0.28
    Ne
    0.25
    402
    0.24
     om
    0.23
     Sioux
    0.23
     Om
    0.20
    Activations Density 0.044%

    No Known Activations