© 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. 28-LLAMASCOPE-RES-32K
    11. 17613
    Prev
    Next
    INDEX
    Explanations

    instances of the word "see" and its variations, reflecting themes of perception and observation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soever
    -0.18
    rien
    -0.18
    .synthetic
    -0.16
    phere
    -0.15
    serie
    -0.15
    ces
    -0.15
    cul
    -0.15
    fts
    -0.15
     ÑģÑĢедÑģÑĤва
    -0.14
    sole
    -0.14
    POSITIVE LOGITS
    /he
    0.36
     fit
    0.25
     how
    0.25
    dust
    0.25
     evidence
    0.23
    /read
    0.21
    -through
    0.20
     cref
    0.19
     Clearly
    0.19
    kest
    0.18
    Activations Density 0.152%

    No Known Activations