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. 19268
    Prev
    Next
    INDEX
    Explanations

    terms related to mid-Atlantic geological and marine research

    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
    :animated
    -0.13
     Aer
    -0.12
    adas
    -0.12
     赤
    -0.12
    asio
    -0.12
     Äijai
    -0.11
    ortic
    -0.11
    à¥Ģदव
    -0.11
    éĭ¼
    -0.11
    /******/
    -0.11
    POSITIVE LOGITS
     AT
    0.97
     At
    0.90
    AT
    0.87
     att
    0.83
     Att
    0.81
    -at
    0.79
    att
    0.76
    _At
    0.75
    _AT
    0.75
    At
    0.75
    Activations Density 0.614%

    No Known Activations