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. 23-LLAMASCOPE-RES-32K
    6. 11656
    Prev
    Next
    INDEX
    Explanations

    elements and attributes commonly used in programming and coding contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    None
    -0.24
    	None
    -0.22
     None
    -0.22
    _None
    -0.20
    none
    -0.19
    (None
    -0.19
    NONE
    -0.18
    odash
    -0.17
     NONE
    -0.17
    =None
    -0.16
    POSITIVE LOGITS
     true
    0.61
    true
    0.52
    (true
    0.49
    	true
    0.45
    :true
    0.41
    =true
    0.40
    >true
    0.38
     True
    0.37
     TRUE
    0.35
    ,true
    0.35
    Activations Density 0.077%

    No Known Activations