© 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. 28-LLAMASCOPE-RES-32K
    11. 29567
    Prev
    Next
    INDEX
    Explanations

    proper names, particularly those associated with medical professionals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mast
    -0.20
     Morrison
    -0.20
     magnet
    -0.19
    mime
    -0.19
     Mast
    -0.19
     Mastery
    -0.19
    mute
    -0.18
     magnets
    -0.18
    mint
    -0.17
    mast
    -0.17
    POSITIVE LOGITS
     MD
    0.84
    MD
    0.73
     md
    0.68
    md
    0.61
     Md
    0.60
    _md
    0.59
    _MD
    0.57
    -md
    0.56
    .md
    0.56
    Md
    0.54
    Activations Density 0.023%

    No Known Activations