© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 26-LLAMASCOPE-RES-32K
    11. 4778
    Prev
    Next
    INDEX
    Explanations

    specific geographic references and locations related to the African American Civil War Memorial and Museum in Washington, D.C

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Washington
    -0.27
    Washington
    -0.23
     Wash
    -0.22
     washington
    -0.20
     DC
    -0.19
     wash
    -0.18
    _DC
    -0.18
    _dc
    -0.17
    apel
    -0.16
    DC
    -0.15
    POSITIVE LOGITS
     Dup
    0.18
     Eck
    0.17
     Wisconsin
    0.17
    Dup
    0.17
    yon
    0.15
    nier
    0.15
     blink
    0.14
    iske
    0.14
     Connecticut
    0.14
    âĨij
    0.14
    Activations Density 0.021%

    No Known Activations