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. 16-LLAMASCOPE-RES-32K
    6. 8161
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize quantities and the relationships between them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istrovstvÃŃ
    -0.17
     mạch
    -0.15
    iverz
    -0.15
    ayet
    -0.14
    Winvalid
    -0.14
    Když
    -0.14
    .labelX
    -0.13
    DOMNode
    -0.13
     bootloader
    -0.13
    ToProps
    -0.13
    POSITIVE LOGITS
     directly
    0.21
     even
    0.18
     already
    0.18
    chu
    0.16
    ison
    0.16
     mere
    0.16
    ·
    0.16
    mere
    0.15
     familiar
    0.15
    insky
    0.15
    Activations Density 0.099%

    No Known Activations