© 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. 4-LLAMASCOPE-RES-32K
    11. 15751
    Prev
    Next
    INDEX
    Explanations

    demonstrative pronouns and their connections to other ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ale
    -0.17
    Äĥn
    -0.16
    ides
    -0.15
    annie
    -0.14
    annes
    -0.14
     Leap
    -0.14
    ature
    -0.14
    ensen
    -0.14
     folk
    -0.13
    te
    -0.13
    POSITIVE LOGITS
    oldt
    0.17
    pNet
    0.17
    ê´Ģ
    0.15
    رÛĮÙħ
    0.15
    ulously
    0.14
    arb
    0.14
    ottom
    0.14
    hall
    0.14
    itution
    0.14
    ikel
    0.14
    Activations Density 0.037%

    No Known Activations