© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 16-LLAMASCOPE-RES-32K
    11. 6706
    Prev
    Next
    INDEX
    Explanations

    concepts related to the evaluation and classification of claims and contributions based on power dynamics and societal structures

    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
    enan
    -0.15
    allon
    -0.14
    nowrap
    -0.14
    legg
    -0.14
    ¼
    -0.14
    åįĵ
    -0.14
    edef
    -0.13
    _runner
    -0.13
     discontin
    -0.13
    zes
    -0.13
    POSITIVE LOGITS
    ç¨ĭ度
    0.30
     degree
    0.29
    degree
    0.26
     depending
    0.25
     extent
    0.24
     level
    0.23
     Degree
    0.22
     degrees
    0.21
    extent
    0.21
    Degree
    0.21
    Activations Density 0.256%

    No Known Activations