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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16817
    Prev
    Next
    INDEX
    Explanations

    specific names and titles related to people, particularly in academic and professional contexts

    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
     kah
    -0.18
    anske
    -0.16
     Zucker
    -0.15
    rouw
    -0.15
     Mehr
    -0.15
     milfs
    -0.15
    irts
    -0.15
    à¸ķา
    -0.15
    agne
    -0.15
    à¸ģรรม
    -0.14
    POSITIVE LOGITS
    pill
    0.28
     Pill
    0.26
     Pitch
    0.23
     Sound
    0.23
     Sel
    0.22
     Ven
    0.22
    iah
    0.22
    -pill
    0.22
     Sund
    0.22
     Sub
    0.21
    Activations Density 0.332%

    No Known Activations