© 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. 10047
    Prev
    Next
    INDEX
    Explanations

    instances of lying down or reclined positions

    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
    á»ijt
    -0.16
    icros
    -0.16
     Hanging
    -0.15
     vlas
    -0.14
    ÅŁa
    -0.14
     Standing
    -0.14
     fing
    -0.14
    Å¡il
    -0.14
    opard
    -0.14
     temel
    -0.14
    POSITIVE LOGITS
     lying
    0.31
     lie
    0.30
     spraw
    0.28
     Lie
    0.25
     flat
    0.25
     lay
    0.25
     prone
    0.24
    flat
    0.23
     lies
    0.23
    Lie
    0.23
    Activations Density 0.094%

    No Known Activations