© 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. 10-LLAMASCOPE-RES-32K
    6. 23724
    Prev
    Next
    INDEX
    Explanations

    references to software modules and components in a coding context

    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
    atra
    -0.15
     Seth
    -0.14
     Nile
    -0.14
    епÑĤи
    -0.14
    appy
    -0.14
    ensis
    -0.14
    Bid
    -0.13
    ovel
    -0.13
    Ä
    -0.13
    otes
    -0.13
    POSITIVE LOGITS
    vrier
    0.17
    onu
    0.16
    ableViewController
    0.14
    iculty
    0.14
    oldt
    0.13
    antee
    0.13
    ünk
    0.13
    stamp
    0.13
    ridge
    0.13
    azzo
    0.13
    Activations Density 0.051%

    No Known Activations