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

    Neuronpedia

    Jacobian LensNEW
    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. 30-LLAMASCOPE-RES-32K
    11. 25744
    Prev
    Next
    INDEX
    Explanations

    frequency of the term "circ" and its variations, indicating a focus on circular themes or cycles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ëĵĿ
    -0.16
    endas
    -0.15
    ippi
    -0.15
    156
    -0.15
    plnÄĽ
    -0.14
    ivery
    -0.14
    oine
    -0.14
    ettings
    -0.14
    zd
    -0.14
     Neu
    -0.14
    POSITIVE LOGITS
    adian
    0.35
    uits
    0.31
    ulatory
    0.30
    ums
    0.28
    led
    0.28
    uito
    0.26
    ulating
    0.26
    ulations
    0.25
    ump
    0.24
    um
    0.24
    Activations Density 0.007%

    No Known Activations