© 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 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. 23-LLAMASCOPE-RES-32K
    11. 29715
    Prev
    Next
    INDEX
    Explanations

    references to the term "Hind" and its variations, usually in relation to individuals or entities associated with Hindu culture or identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nob
    -0.17
    er
    -0.16
    s
    -0.16
    ãĥįãĥ«
    -0.16
    nel
    -0.15
    inta
    -0.15
     Sun
    -0.15
    andra
    -0.15
     charge
    -0.14
    alet
    -0.14
    POSITIVE LOGITS
    rance
    0.29
    enburg
    0.27
    rances
    0.27
    quarters
    0.20
    ustrial
    0.18
    reds
    0.18
    Ùħار
    0.17
    ost
    0.17
    ust
    0.17
     Hind
    0.17
    Activations Density 0.012%

    No Known Activations