© 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. 30-LLAMASCOPE-RES-32K
    11. 11651
    Prev
    Next
    INDEX
    Explanations

    apostrophes in words, particularly in possessive forms and contractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulet
    -0.16
    ÙĦس
    -0.16
    Ãłng
    -0.15
    æľŃ
    -0.15
    ungs
    -0.15
    .secret
    -0.15
    outers
    -0.14
    ÑģÑĤ
    -0.14
     ple
    -0.14
    ernes
    -0.14
    POSITIVE LOGITS
    ourke
    0.30
    ullivan
    0.28
     Sullivan
    0.25
     Connor
    0.24
    Connell
    0.23
     Shea
    0.23
     Ri
    0.22
     Conor
    0.21
     Sha
    0.21
    hea
    0.21
    Activations Density 0.008%

    No Known Activations