© 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. 28321
    Prev
    Next
    INDEX
    Explanations

    references to political concepts and discussions

    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
     Politics
    -0.31
     politics
    -0.31
     politic
    -0.28
     POLIT
    -0.27
     politically
    -0.27
     Political
    -0.26
     politik
    -0.26
     politique
    -0.25
     political
    -0.25
     polÃŃtica
    -0.25
    POSITIVE LOGITS
     correctness
    0.32
     incorrect
    0.26
     Incorrect
    0.24
     Correct
    0.23
     scientist
    0.22
    -economic
    0.22
    incorrect
    0.21
     parties
    0.21
     prisoners
    0.21
    /legal
    0.20
    Activations Density 0.036%

    No Known Activations