© 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. 2-LLAMASCOPE-RES-32K
    11. 5540
    Prev
    Next
    INDEX
    Explanations

    references to STEM (Science, Technology, Engineering, and Mathematics) fields and education

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ppers
    -0.16
    ysa
    -0.16
    attend
    -0.16
    /Core
    -0.16
    ngo
    -0.16
    stri
    -0.15
    getManager
    -0.15
    zel
    -0.15
    TEE
    -0.15
     Fowler
    -0.14
    POSITIVE LOGITS
    499
    0.16
    918
    0.16
     khai
    0.14
    داد
    0.14
    setLabel
    0.14
    baar
    0.14
    uada
    0.14
    ARK
    0.14
    uC
    0.14
    cke
    0.13
    Activations Density 0.002%

    No Known Activations