© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 10-LLAMASCOPE-RES-32K
    11. 19992
    Prev
    Next
    INDEX
    Explanations

    multi-word phrases or combinations that suggest hierarchy, organization, or significant influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wner
    -0.17
    oyer
    -0.16
    erap
    -0.16
    subst
    -0.14
    PIO
    -0.14
    ucas
    -0.14
    rei
    -0.14
    wright
    -0.14
    æĥħ
    -0.14
    esus
    -0.14
    POSITIVE LOGITS
    armed
    0.17
    anj
    0.16
    .MockMvc
    0.15
    agger
    0.15
     Moss
    0.14
    argins
    0.14
     Loot
    0.14
     underage
    0.14
     tw
    0.14
    -too
    0.13
    Activations Density 0.268%

    No Known Activations