© 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. 21-LLAMASCOPE-RES-32K
    11. 16717
    Prev
    Next
    INDEX
    Explanations

    medical or health-related conditions and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quite
    -0.22
     both
    -0.21
     each
    -0.19
     probably
    -0.19
     almost
    -0.19
     if
    -0.18
     Quite
    -0.18
     Various
    -0.17
     nearly
    -0.17
     various
    -0.16
    POSITIVE LOGITS
     ANY
    0.30
    anything
    0.27
     yoksa
    0.26
     _______,
    0.26
    ï¼ĮåĪĻ
    0.25
     anything
    0.25
    à¹ĥà¸Ķ
    0.25
     nÃło
    0.24
    æŁIJ
    0.24
    (any
    0.23
    Activations Density 0.631%

    No Known Activations