© 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. 20410
    Prev
    Next
    INDEX
    Explanations

    patterns related to options and choices

    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
    odem
    -0.15
    asma
    -0.15
    ultz
    -0.14
    typeorm
    -0.14
    agnost
    -0.14
    alah
    -0.14
    ÎłÎij
    -0.14
    олоÑĤ
    -0.13
    apk
    -0.13
    bose
    -0.13
    POSITIVE LOGITS
     among
    0.64
     amongst
    0.56
    among
    0.54
     Among
    0.47
    Among
    0.43
     ÑģÑĢеди
    0.37
     from
    0.36
    FromArray
    0.28
    from
    0.26
    åħ¶ä¸Ń
    0.26
    Activations Density 0.170%

    No Known Activations