© 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. 19639
    Prev
    Next
    INDEX
    Explanations

    issues related to problem identification and resolution

    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
    Reuse
    -0.18
    reuse
    -0.15
    loff
    -0.14
    (ConfigurationManager
    -0.14
    .mount
    -0.14
    覧
    -0.13
     Reduction
    -0.13
    _Util
    -0.13
     reuse
    -0.13
    adow
    -0.13
    POSITIVE LOGITS
     fix
    0.75
     fixes
    0.69
    fix
    0.69
     fixing
    0.68
     Fix
    0.66
     fixed
    0.65
    -fix
    0.65
    Fix
    0.65
     FIX
    0.59
    _fix
    0.59
    Activations Density 0.565%

    No Known Activations