© 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. 16-LLAMASCOPE-RES-32K
    11. 17678
    Prev
    Next
    INDEX
    Explanations

    concepts related to academic writing and the dissertation process

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ãĥĸãĥª
    -0.14
    ÑĥÑĩа
    -0.14
    idges
    -0.13
    oldem
    -0.13
    thers
    -0.13
     Möglich
    -0.13
    æĬľ
    -0.13
    hh
    -0.12
    ablish
    -0.12
    .ads
    -0.12
    POSITIVE LOGITS
    enate
    0.15
    cape
    0.15
    dbe
    0.15
    rug
    0.15
    engeance
    0.15
    ainen
    0.14
    phem
    0.13
    byn
    0.13
    ods
    0.13
    ohen
    0.13
    Activations Density 0.039%

    No Known Activations