© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 28-LLAMASCOPE-RES-32K
    11. 17508
    Prev
    Next
    INDEX
    Explanations

    phrases indicating questions or uncertainty regarding events, statements, or decisions, particularly in relation to social and political contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    toMatch
    -0.14
    shouldBe
    -0.14
    ==="
    -0.13
    inan
    -0.12
     (!!
    -0.12
    Į¨
    -0.12
    .fromFunction
    -0.11
    IsEmpty
    -0.11
    undan
    -0.11
     XCTAssertTrue
    -0.11
    POSITIVE LOGITS
     not
    1.26
    not
    0.96
     NOT
    0.93
     Not
    0.84
    Not
    0.80
     не
    0.74
     nicht
    0.74
    	not
    0.73
    _not
    0.73
    -not
    0.71
    Activations Density 2.154%

    No Known Activations