© 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. 20-LLAMASCOPE-RES-32K
    11. 28747
    Prev
    Next
    INDEX
    Explanations

    terms related to biological structures and functions, specifically focusing on lamins and their implications in diseases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ẩu
    -0.16
    ivant
    -0.15
    .RecyclerView
    -0.15
    prak
    -0.15
     nested
    -0.14
    _vlog
    -0.14
    ify
    -0.14
    imation
    -0.14
    lements
    -0.14
    erno
    -0.13
    POSITIVE LOGITS
     fruit
    0.24
     flies
    0.23
     fly
    0.21
     yeast
    0.21
     Arab
    0.20
    fruit
    0.20
    flies
    0.19
    Fly
    0.19
     organisms
    0.19
    enor
    0.19
    Activations Density 0.112%

    No Known Activations