© 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. 32281
    Prev
    Next
    INDEX
    Explanations

    references to images or links within the text

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    engo
    -0.17
    wow
    -0.15
    rim
    -0.15
     Mech
    -0.15
     DÃŃky
    -0.15
    acket
    -0.15
    aler
    -0.14
    ods
    -0.14
    aight
    -0.14
    roe
    -0.14
    POSITIVE LOGITS
     Nam
    0.17
    Nam
    0.16
    hti
    0.15
     inverted
    0.14
    Å¡t
    0.14
    artz
    0.14
     MISS
    0.14
    stin
    0.13
    770
    0.13
    ervlet
    0.13
    Activations Density 0.014%

    No Known Activations