© 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. 31-LLAMASCOPE-RES-32K
    11. 22048
    Prev
    Next
    INDEX
    Explanations

    adjectives describing various qualities, especially those with negative connotations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ively
    -0.23
    able
    -0.21
    nal
    -0.20
    ible
    -0.18
    st
    -0.17
    lessly
    -0.17
    ers
    -0.17
    ually
    -0.17
    ably
    -0.17
    ive
    -0.16
    POSITIVE LOGITS
     little
    0.29
    -eyed
    0.28
    lic
    0.26
    -haired
    0.26
    town
    0.25
    grams
    0.24
    -faced
    0.24
    yyy
    0.24
    eyed
    0.24
     haired
    0.24
    Activations Density 0.153%

    No Known Activations