© 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. 31-LLAMASCOPE-RES-32K
    6. 3200
    Prev
    Next
    INDEX
    Explanations

    unique characters or symbols within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.68
     in
    -0.61
     and
    -0.58
     on
    -0.54
     to
    -0.54
     a
    -0.52
     or
    -0.51
     as
    -0.50
     for
    -0.49
    .
    -0.48
    POSITIVE LOGITS
     ÑģоÑģÑĤав
    0.24
     ÑģоÑģÑĤавлÑıеÑĤ
    0.22
     naopak
    0.22
     наÑģ
    0.22
     WHATSOEVER
    0.21
     обÑī
    0.20
     возÑĢаÑģÑĤ
    0.20
     jaký
    0.20
    chartInstance
    0.20
    اÙĪÙĨد
    0.19
    Activations Density 0.005%

    No Known Activations