© 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. 28-LLAMASCOPE-RES-32K
    11. 23609
    Prev
    Next
    INDEX
    Explanations

    references to musical performances and the experiences associated with them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avo
    -0.15
    habi
    -0.15
    Äĥm
    -0.15
    ederland
    -0.15
    Bundle
    -0.15
    akt
    -0.15
    .bundle
    -0.14
    ieri
    -0.14
    SYM
    -0.14
    رÛĮز
    -0.14
    POSITIVE LOGITS
     sing
    0.40
     belt
    0.37
     cro
    0.36
     belts
    0.35
    belt
    0.34
     Sang
    0.34
     sang
    0.33
     Belt
    0.33
     bel
    0.32
    Sing
    0.30
    Activations Density 0.121%

    No Known Activations