© 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. 20-LLAMASCOPE-RES-32K
    11. 27855
    Prev
    Next
    INDEX
    Explanations

    words related to affiliation and relationships between entities or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erset
    -0.16
    270
    -0.16
    itude
    -0.16
    apult
    -0.16
    achuset
    -0.14
    enou
    -0.14
    erged
    -0.14
    arda
    -0.14
    Readable
    -0.14
    åĬŀ
    -0.14
    POSITIVE LOGITS
     Par
    0.35
    -par
    0.33
     par
    0.32
    Par
    0.32
     PAR
    0.30
     Parsons
    0.28
    .par
    0.28
    par
    0.27
    PAR
    0.26
    (par
    0.26
    Activations Density 0.047%

    No Known Activations