© 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. 28098
    Prev
    Next
    INDEX
    Explanations

    references to organizations and their involvement in advocacy or calls for action

    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
    ossip
    -0.15
    erif
    -0.14
     confession
    -0.14
    íĥķ
    -0.14
    Confirm
    -0.14
    æ¿ĥ
    -0.14
    confirm
    -0.13
    лиж
    -0.13
     Rum
    -0.13
    -src
    -0.13
    POSITIVE LOGITS
     call
    0.30
     calling
    0.29
     pressing
    0.28
     calls
    0.28
     imp
    0.27
     urge
    0.27
    åij¼
    0.27
     urges
    0.25
     push
    0.25
     demands
    0.25
    Activations Density 0.476%

    No Known Activations