© 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. 18-LLAMASCOPE-RES-32K
    11. 25140
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, particularly those with the name "Kat" or variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ollo
    -0.15
     Lac
    -0.14
    iciary
    -0.14
    eca
    -0.14
     sac
    -0.14
    ICI
    -0.14
    539
    -0.14
    ắt
    -0.14
    ["_
    -0.14
    847
    -0.13
    POSITIVE LOGITS
    owitz
    0.19
    rink
    0.17
    ziej
    0.17
     vice
    0.15
    Flash
    0.14
    ainen
    0.14
    ä»ĺ
    0.14
    妮
    0.14
    apolis
    0.14
    ار
    0.14
    Activations Density 0.032%

    No Known Activations