© 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. 25-LLAMASCOPE-RES-32K
    6. 23133
    Prev
    Next
    INDEX
    Explanations

    terms related to weather phenomena and scientific observations of environmental conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ellig
    -0.16
     thi
    -0.15
    .wp
    -0.15
    .grp
    -0.15
    lij
    -0.15
     Mov
    -0.15
    ãĥ¼ãĥĭ
    -0.14
     stuffed
    -0.14
     fluct
    -0.14
     ple
    -0.14
    POSITIVE LOGITS
    forcing
    0.21
     forcing
    0.19
     climate
    0.19
    Cou
    0.19
     diagnosed
    0.18
    å°º
    0.18
     Paleo
    0.18
     Ensemble
    0.18
     assim
    0.18
     IPCC
    0.18
    Activations Density 0.117%

    No Known Activations