© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 16-LLAMASCOPE-RES-32K
    11. 8163
    Prev
    Next
    INDEX
    Explanations

    phrases related to pricing and value propositions in products

    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
    ë¶Ī
    -0.18
    682
    -0.18
     pedal
    -0.16
    ippi
    -0.15
    FromBody
    -0.14
    ceed
    -0.14
    .qq
    -0.14
    SHIFT
    -0.14
     Ped
    -0.14
     Hat
    -0.14
    POSITIVE LOGITS
     price
    0.34
     prices
    0.28
    price
    0.26
    PRICE
    0.26
     Price
    0.24
    Price
    0.24
    .price
    0.24
     Prices
    0.23
    ä¾¡æł¼
    0.23
     PRICE
    0.23
    Activations Density 0.148%

    No Known Activations