© 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. 4-LLAMASCOPE-RES-32K
    11. 30718
    Prev
    Next
    INDEX
    Explanations

    comparative language and expressions of magnitude or size

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .mx
    -0.17
    ála
    -0.15
     Nguyen
    -0.15
    _allowed
    -0.14
    ly
    -0.13
    ìĿ´ìŀIJ
    -0.13
    UTO
    -0.13
    theid
    -0.13
    uet
    -0.13
    ête
    -0.13
    POSITIVE LOGITS
     than
    0.28
    -than
    0.24
    than
    0.23
    _than
    0.19
     än
    0.18
    Than
    0.17
     THAN
    0.17
     než
    0.17
     Than
    0.16
     Bowen
    0.15
    Activations Density 0.299%

    No Known Activations