© 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. 29-LLAMASCOPE-RES-32K
    11. 226
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the removal or eradication of negative concepts or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reopened
    -0.19
     reopening
    -0.18
    _Delay
    -0.18
     slowdown
    -0.17
    reopen
    -0.15
     prolong
    -0.15
    937
    -0.15
    eca
    -0.15
    ÙĨدÛĮ
    -0.14
     povol
    -0.14
    POSITIVE LOGITS
     rid
    0.57
     eliminate
    0.57
     elimination
    0.52
     elim
    0.51
     eliminating
    0.50
     Elim
    0.49
     eliminates
    0.47
    Elim
    0.47
     remove
    0.46
    elim
    0.45
    Activations Density 0.624%

    No Known Activations