© 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. 25-LLAMASCOPE-RES-32K
    11. 22870
    Prev
    Next
    INDEX
    Explanations

    phrases related to exclusive offers or limited availability items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opyright
    -0.14
    ORN
    -0.14
    à¥ģध
    -0.14
     dil
    -0.14
    emachine
    -0.14
     fread
    -0.13
     Precision
    -0.13
     cond
    -0.13
     Brands
    -0.13
    brands
    -0.13
    POSITIVE LOGITS
     pledge
    0.24
     pled
    0.23
     rewards
    0.23
     reward
    0.23
     backers
    0.23
     pledges
    0.22
    pled
    0.22
     tiers
    0.20
     Reward
    0.20
     Supporters
    0.19
    Activations Density 0.018%

    No Known Activations