© 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. 18285
    Prev
    Next
    INDEX
    Explanations

    negations and phrases expressing impossibility or prohibition

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ullo
    -0.17
    ucken
    -0.16
    iar
    -0.15
    ote
    -0.15
     Gand
    -0.14
    ulling
    -0.14
    illa
    -0.14
    ubs
    -0.14
    ogan
    -0.14
    illing
    -0.14
    POSITIVE LOGITS
    leccion
    0.16
    storybook
    0.14
    primer
    0.14
    éłĵ
    0.14
    ottage
    0.14
    AccessException
    0.14
     اÙĦجÙĨ
    0.14
     Stanley
    0.14
    NgModule
    0.14
     //~
    0.14
    Activations Density 0.140%

    No Known Activations