© 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. 2-LLAMASCOPE-RES-32K
    11. 12421
    Prev
    Next
    INDEX
    Explanations

    references to different types of glass or glass-related objects in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     å©
    -0.16
    ترÙĥ
    -0.15
    NOP
    -0.14
    reen
    -0.14
    ols
    -0.14
    adero
    -0.14
    ±
    -0.14
    urv
    -0.14
    uli
    -0.14
    OLS
    -0.14
    POSITIVE LOGITS
    atan
    0.17
    ureau
    0.17
     ëĭ¤ìļ´ë°Ľê¸°
    0.15
    ÑĩиÑģл
    0.14
    apur
    0.14
    anners
    0.14
    nett
    0.14
     Stem
    0.14
    heid
    0.14
     ann
    0.14
    Activations Density 0.022%

    No Known Activations