© 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. 30-LLAMASCOPE-RES-32K
    11. 17855
    Prev
    Next
    INDEX
    Explanations

    references to birth and death statistics

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    -Clause
    -0.16
    stinence
    -0.15
    egend
    -0.14
    rog
    -0.14
    achment
    -0.14
    åŁ
    -0.14
    ocket
    -0.14
     forth
    -0.14
    eper
    -0.14
    warz
    -0.14
    POSITIVE LOGITS
     establishments
    0.29
     births
    0.25
     Establish
    0.22
    ëħĦ
    0.19
     establishment
    0.19
    å¹´
    0.19
     год
    0.18
     deaths
    0.17
    -ci
    0.17
    TemplateName
    0.17
    Activations Density 0.012%

    No Known Activations