© 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. 11-LLAMASCOPE-RES-32K
    11. 28445
    Prev
    Next
    INDEX
    Explanations

    names of people, particularly those of Asian descent or origin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    athom
    -0.18
    òng
    -0.14
    illas
    -0.14
     Marty
    -0.14
     charged
    -0.14
    ctors
    -0.14
    yas
    -0.13
     ÑĤÑĢÑĥб
    -0.13
    dere
    -0.13
    ecz
    -0.13
    POSITIVE LOGITS
    averse
    0.16
    ãģıãĤĵ
    0.15
    ayscale
    0.14
    иÑģÑĤÑĢа
    0.14
    %p
    0.14
    [".
    0.14
    вÑĸÑĤ
    0.13
    SON
    0.13
     trp
    0.13
     Medina
    0.13
    Activations Density 0.023%

    No Known Activations