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. 30-LLAMASCOPE-RES-32K
    6. 22142
    Prev
    Next
    INDEX
    Explanations

    information related to economic and community development initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Five
    -0.14
    _Zero
    -0.14
     Eleven
    -0.14
    ä¸īä¸ī
    -0.13
    -three
    -0.13
    Seven
    -0.13
     nineteenth
    -0.13
    Four
    -0.13
    Three
    -0.13
    รรà¸Ħ
    -0.13
    POSITIVE LOGITS
     thousands
    0.66
     hundreds
    0.66
     over
    0.66
     more
    0.57
     tens
    0.56
     nearly
    0.53
     around
    0.53
     approximately
    0.51
     Thousands
    0.47
     about
    0.46
    Activations Density 1.008%

    No Known Activations