© 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. 20-LLAMASCOPE-RES-32K
    11. 22178
    Prev
    Next
    INDEX
    Explanations

    references to celebrations or events characterized by displays of power or force

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     which
    -0.16
    OLLOW
    -0.16
     obviously
    -0.15
     wake
    -0.15
     Which
    -0.15
    Which
    -0.14
    ï¼Į以åıĬ
    -0.14
    izm
    -0.14
    irie
    -0.14
    ambre
    -0.13
    POSITIVE LOGITS
    /,
    0.19
    ®,
    0.17
    (),
    0.17
    ÙĭØĮ
    0.16
    {},
    0.16
     _,
    0.16
    GuidId
    0.16
    piler
    0.16
    !,
    0.16
    %,
    0.16
    Activations Density 0.274%

    No Known Activations