© 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. 22351
    Prev
    Next
    INDEX
    Explanations

    concepts related to pantry organization and design

    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
    @qq
    -0.15
     Cater
    -0.14
    üss
    -0.14
    iffin
    -0.14
    elper
    -0.14
    åĩĮ
    -0.13
    agli
    -0.13
    chio
    -0.13
    Ä±ÅŁÄ±k
    -0.13
     rather
    -0.13
    POSITIVE LOGITS
    erti
    0.14
    ç³»
    0.14
    ãĤĨ
    0.14
    -aos
    0.14
    Fi
    0.13
    ãĤ¹ãĤ¯
    0.13
    inis
    0.13
     ä¿®
    0.13
     Ùģار
    0.13
    bian
    0.13
    Activations Density 0.014%

    No Known Activations