© 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. 10-LLAMASCOPE-RES-32K
    11. 20310
    Prev
    Next
    INDEX
    Explanations

    sentences starting with the word "Yeah."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    issent
    -0.15
    oftware
    -0.15
    intelligence
    -0.14
    .pt
    -0.14
    INY
    -0.14
    XB
    -0.14
    boot
    -0.14
    intree
    -0.14
    iple
    -0.14
    ancell
    -0.14
    POSITIVE LOGITS
    ìĥģìĿĦ
    0.13
    lients
    0.13
    atta
    0.13
    rov
    0.13
     assorted
    0.13
     UTIL
    0.12
    834
    0.12
    oblin
    0.12
    à¹Ĩ
    0.12
    spor
    0.12
    Activations Density 0.080%

    No Known Activations