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. 12-LLAMASCOPE-RES-32K
    6. 13825
    Prev
    Next
    INDEX
    Explanations

    concepts related to charity, needs, and personal growth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esson
    -0.18
    increments
    -0.15
     æĸ
    -0.15
    ajs
    -0.15
    омен
    -0.15
    urga
    -0.15
    eniz
    -0.15
    iste
    -0.14
    ajas
    -0.14
    à¥ĩशà¤ķ
    -0.14
    POSITIVE LOGITS
     of
    0.18
     cá»§a
    0.17
    άνι
    0.15
    ÑĢаÑģÑĤа
    0.14
    ospace
    0.14
    beb
    0.14
    ustry
    0.14
    963
    0.14
    stp
    0.14
    ased
    0.13
    Activations Density 0.262%

    No Known Activations