© 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. 25-LLAMASCOPE-RES-32K
    11. 22209
    Prev
    Next
    INDEX
    Explanations

    references to childhood television shows, particularly "Full House."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     downtown
    -0.15
     åĥ
    -0.15
    sect
    -0.14
     Erotik
    -0.14
    Adapter
    -0.14
     ech
    -0.14
     Greenwood
    -0.14
    izzle
    -0.14
    kü
    -0.14
    zahl
    -0.13
    POSITIVE LOGITS
     Sit
    0.18
     Bund
    0.16
     Modern
    0.15
    sched
    0.15
    Sit
    0.15
    à¹Ģลย
    0.15
     sitcom
    0.15
    loor
    0.14
    ãģĤãģĤ
    0.14
    stantiate
    0.14
    Activations Density 0.049%

    No Known Activations