© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18459
    Prev
    Next
    INDEX
    Explanations

    references to specific bands or musicians in the context of their history and influence

    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
    ÙħارÛĮ
    -0.14
    lue
    -0.14
    achat
    -0.14
     Boundary
    -0.14
    redo
    -0.14
    spiel
    -0.14
    ustos
    -0.14
    Functional
    -0.13
    åľ
    -0.13
    Teams
    -0.13
    POSITIVE LOGITS
     lead
    0.54
     front
    0.48
    lead
    0.48
     Lead
    0.44
    Lead
    0.42
     bass
    0.39
     keyboard
    0.39
    front
    0.38
     fronts
    0.35
     leader
    0.34
    Activations Density 0.227%

    No Known Activations