Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 28-LLAMASCOPE-RES-32K
    6. 28938
    Prev
    Next
    INDEX
    Explanations

    commands and terms related to software development, particularly in frameworks like Rails and tools like Docker

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arra
    -0.15
    aras
    -0.14
    ÑĦик
    -0.13
    iguous
    -0.13
    DOCUMENT
    -0.13
     Chun
    -0.13
    feito
    -0.13
     Sink
    -0.13
    Registr
    -0.13
     Pick
    -0.13
    POSITIVE LOGITS
    .exe
    0.31
    .bat
    0.25
    .cmd
    0.24
    .EX
    0.22
    ectl
    0.20
     commands
    0.20
    /bin
    0.20
     ARGS
    0.20
    åij½ä»¤
    0.19
    .py
    0.19
    Activations Density 0.069%

    No Known Activations