© 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. 28330
    Prev
    Next
    INDEX
    Explanations

    phrases related to accessibility and ease of implementation 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 @ 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
    IPS
    -0.14
     mÃŃt
    -0.14
    YM
    -0.14
    inati
    -0.14
    Exact
    -0.14
    solete
    -0.13
    Та
    -0.13
     Haven
    -0.13
    oose
    -0.13
    getManager
    -0.13
    POSITIVE LOGITS
    åı¯
    0.37
     retrie
    0.34
     ÙĤابÙĦ
    0.33
     deploy
    0.32
     drawable
    0.32
    etable
    0.31
    vable
    0.30
     amend
    0.30
     recover
    0.29
    atable
    0.29
    Activations Density 0.506%

    No Known Activations