© 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. 20-LLAMASCOPE-RES-32K
    11. 32539
    Prev
    Next
    INDEX
    Explanations

    references to former individuals in various contexts, particularly those with notable titles or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    former
    -0.28
     former
    -0.24
    Former
    -0.24
     Former
    -0.23
     older
    -0.18
     formerly
    -0.17
     Older
    -0.17
    yy
    -0.16
    缮åīį
    -0.15
    ba
    -0.15
    POSITIVE LOGITS
    /current
    0.29
    /new
    0.20
    odus
    0.18
    ly
    0.17
    /original
    0.17
    yme
    0.17
    ebin
    0.16
    lies
    0.16
     incarnation
    0.16
    ãĢħ
    0.16
    Activations Density 0.031%

    No Known Activations