© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 14-LLAMASCOPE-RES-32K
    11. 28786
    Prev
    Next
    INDEX
    Explanations

    references to authority and reporting structures within an organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apas
    -0.15
    .gg
    -0.14
    olec
    -0.14
    vie
    -0.14
    olla
    -0.14
    nech
    -0.13
     Clerk
    -0.13
    upa
    -0.13
    ĥĿ
    -0.13
     ++)
    -0.13
    POSITIVE LOGITS
     higher
    0.21
     senior
    0.18
    higher
    0.18
    ingham
    0.18
     highest
    0.18
     owner
    0.17
     top
    0.17
     upper
    0.16
     Owner
    0.16
     macro
    0.16
    Activations Density 0.192%

    No Known Activations