© 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. 19-LLAMASCOPE-RES-32K
    6. 30444
    Prev
    Next
    INDEX
    Explanations

    references to programming collaboration and advice on software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _ISO
    -0.16
     hel
    -0.15
    instanc
    -0.14
    _USB
    -0.14
     ISO
    -0.14
     ener
    -0.14
    vÄĽÅĻ
    -0.14
    ocide
    -0.14
     USB
    -0.13
    лив
    -0.13
    POSITIVE LOGITS
    von
    0.21
     computer
    0.20
     Computer
    0.20
    computer
    0.19
     Lisp
    0.19
     Programming
    0.19
    Computer
    0.18
    abbage
    0.18
     machine
    0.17
    machine
    0.17
    Activations Density 0.068%

    No Known Activations