© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-32K
    6. 16796
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to natural health and wellness treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸ŃæĸĩåŃĹå¹ķ
    -0.29
    ç½ijåĪĬ
    -0.27
    éĺħ读次æķ°
    -0.25
    éĽħé»ij
    -0.23
    ï¼ģ",
    -0.22
     ç¥ŀ马
    -0.22
    ãĢĤwww
    -0.21
    ãĢij,ãĢIJ
    -0.20
    ï¼ģï¼ģ↵↵
    -0.19
    çͳåįļ
    -0.19
    POSITIVE LOGITS
    å°Ĩ
    0.28
    åľ¨
    0.26
    使ç͍
    0.26
    è¿Ľè¡Į
    0.26
    æĬĬ
    0.25
    使
    0.24
    åĨį
    0.24
    以
    0.24
    éĢļè¿ĩ
    0.24
    让
    0.24
    Activations Density 0.005%

    No Known Activations