© 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. 9-LLAMASCOPE-RES-32K
    11. 10226
    Prev
    Next
    INDEX
    Explanations

    references to specific names, titles, and unique identifiers in popular culture

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ony
    -0.17
     sc
    -0.15
    _fwd
    -0.14
     naken
    -0.13
    ory
    -0.13
    ãĥ¼ãĤ¹ãĥĪ
    -0.13
    oy
    -0.13
    icket
    -0.13
     porno
    -0.13
    ẩm
    -0.13
    POSITIVE LOGITS
    å±ĭ
    0.19
    MOOTH
    0.14
    ubre
    0.14
    Ñıд
    0.14
    iard
    0.14
    vÄĽt
    0.14
     Brotherhood
    0.14
     Summers
    0.13
    Ïĥε
    0.13
    LETTE
    0.13
    Activations Density 0.040%

    No Known Activations