© 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. 10160
    Prev
    Next
    INDEX
    Explanations

    the presence of specific regulatory or compliance terms

    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
     Shoot
    -0.15
     grip
    -0.15
    no
    -0.15
     shoot
    -0.14
    ouch
    -0.14
    iset
    -0.14
     mute
    -0.14
    asher
    -0.14
    shoot
    -0.14
     Grip
    -0.14
    POSITIVE LOGITS
    ç©´
    0.18
    оваÑĢ
    0.16
    CallCheck
    0.15
    mium
    0.15
    μη
    0.14
    ç´Ģ
    0.14
    .prevent
    0.14
    meer
    0.14
    QUIRE
    0.14
    ZeroWidthSpace
    0.14
    Activations Density 0.000%

    No Known Activations