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. 30441
    Prev
    Next
    INDEX
    Explanations

    themes related to personal experiences and transitions in life, particularly concerning community involvement and challenges

    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
    illy
    -0.15
    ByExample
    -0.15
    ildo
    -0.14
    ặ
    -0.14
    lap
    -0.14
    Ú¯ÙĪ
    -0.14
    .scenes
    -0.14
    ingles
    -0.14
    indsight
    -0.14
    .subscriptions
    -0.14
    POSITIVE LOGITS
     for
    0.54
    for
    0.41
     forever
    0.35
    	for
    0.35
     ÑĤеÑĩение
    0.34
     longer
    0.34
     longest
    0.32
     briefly
    0.32
     until
    0.31
     untuk
    0.29
    Activations Density 0.592%

    No Known Activations