© 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. 28151
    Prev
    Next
    INDEX
    Explanations

    references to specific codes or classifications related to systems or software

    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
    asaki
    -0.16
    ritt
    -0.16
    udden
    -0.15
     guts
    -0.14
    upal
    -0.14
    upertino
    -0.14
    áÄį
    -0.14
    istrat
    -0.14
    efined
    -0.14
    chied
    -0.13
    POSITIVE LOGITS
    (C
    0.21
    (Common
    0.17
    rese
    0.16
    ISR
    0.16
    pillar
    0.15
    /C
    0.15
    =C
    0.15
     ///</
    0.15
    ,C
    0.15
    atego
    0.15
    Activations Density 0.165%

    No Known Activations