© 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. 26-LLAMASCOPE-RES-32K
    11. 21863
    Prev
    Next
    INDEX
    Explanations

    phrases containing variations of the word "sneak."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .scalablytyped
    -0.21
    uteur
    -0.18
    ocl
    -0.16
    èIJ½ãģ¡
    -0.15
    mits
    -0.15
    pine
    -0.15
    sheet
    -0.15
    aments
    -0.15
    .gwt
    -0.14
    inson
    -0.14
    POSITIVE LOGITS
     sne
    0.31
     Sne
    0.28
    aky
    0.25
    -preview
    0.25
     preview
    0.23
    ily
    0.23
    aking
    0.22
     Peek
    0.22
     peak
    0.21
     Preview
    0.21
    Activations Density 0.007%

    No Known Activations