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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-32K
    6. 11331
    Prev
    Next
    INDEX
    Explanations

    programming-related function definitions and return statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     null
    -0.26
    null
    -0.21
    -null
    -0.16
    uracy
    -0.16
    =true
    -0.15
    ãĥ¥
    -0.15
    typeof
    -0.15
    (null
    -0.14
    	null
    -0.14
    /null
    -0.14
    POSITIVE LOGITS
     None
    0.78
    None
    0.71
    (None
    0.57
    	None
    0.50
     none
    0.48
    _None
    0.47
     True
    0.47
     False
    0.46
    ,None
    0.46
     NONE
    0.43
    Activations Density 0.027%

    No Known Activations