© 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. 18-LLAMASCOPE-RES-32K
    11. 20255
    Prev
    Next
    INDEX
    Explanations

    references to businesses and community services in a geographical area

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    zew
    -0.16
    ombs
    -0.15
    ]=>
    -0.14
    Europe
    -0.14
    chk
    -0.14
    PUTE
    -0.13
     Fayette
    -0.13
     Appalach
    -0.13
     Europe
    -0.13
    spath
    -0.13
    POSITIVE LOGITS
    rott
    0.17
     Mystic
    0.15
     Cook
    0.14
    ãĥ¼ãĥª
    0.14
     Edison
    0.14
    uner
    0.13
     Georgia
    0.13
     Lazy
    0.13
    elp
    0.13
    _lazy
    0.13
    Activations Density 1.041%

    No Known Activations