© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 26-LLAMASCOPE-RES-32K
    6. 28100
    Prev
    Next
    INDEX
    Explanations

    references to CNC (computer numerical control) machinery and its instructions

    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
    jezd
    -0.14
     nailed
    -0.14
     uw
    -0.14
    igham
    -0.14
    IBLE
    -0.14
     Hayward
    -0.14
    enville
    -0.13
    ayım
    -0.13
     Giul
    -0.13
    åħIJ
    -0.13
    POSITIVE LOGITS
     lat
    0.24
     NC
    0.24
     DNC
    0.23
     CNC
    0.22
     gan
    0.21
    NC
    0.21
     milling
    0.21
     Maz
    0.20
     Blanch
    0.20
     Shops
    0.19
    Activations Density 0.018%

    No Known Activations