© 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. 31-LLAMASCOPE-RES-32K
    11. 18681
    Prev
    Next
    INDEX
    Explanations

    terms related to the orientation of athletes in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĿ¯
    -0.17
    ration
    -0.16
     surve
    -0.15
    rava
    -0.15
    incare
    -0.15
    ctal
    -0.14
     Král
    -0.14
    ضÙĪ
    -0.14
    rá
    -0.14
    rab
    -0.14
    POSITIVE LOGITS
    y
    0.38
    ies
    0.32
    -handed
    0.30
    ie
    0.27
    ys
    0.23
    field
    0.23
    -h
    0.23
    iness
    0.21
     field
    0.21
    -footer
    0.20
    Activations Density 0.009%

    No Known Activations