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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 11-LLAMASCOPE-RES-32K
    6. 28583
    Prev
    Next
    INDEX
    Explanations

    verbs indicating actions or processes related to support, cleansing, and transformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yourselves
    -0.17
    etime
    -0.17
     themselves
    -0.17
     ourselves
    -0.15
    c
    -0.15
    Ñķ
    -0.15
    halt
    -0.15
    um
    -0.15
    croft
    -0.15
     selves
    -0.15
    POSITIVE LOGITS
     itself
    0.22
    los
    0.17
    beg
    0.16
    isque
    0.16
    cales
    0.16
    child
    0.16
    dete
    0.15
    ometr
    0.15
     pr
    0.15
    ded
    0.15
    Activations Density 0.563%

    No Known Activations