© 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. 23-LLAMASCOPE-RES-32K
    11. 30096
    Prev
    Next
    INDEX
    Explanations

    references to specific cities, particularly Hong Kong

    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
    acemark
    -0.15
    .liferay
    -0.15
    wright
    -0.15
    agher
    -0.15
    idges
    -0.14
    >NN
    -0.14
    OW
    -0.14
    zens
    -0.14
    εÏĦ
    -0.14
    çł²
    -0.14
    POSITIVE LOGITS
     Kong
    0.31
    콩
    0.17
    isto
    0.15
    çĿĽ
    0.15
     Island
    0.14
    fully
    0.14
    chter
    0.14
    kon
    0.14
    asca
    0.14
    dae
    0.13
    Activations Density 0.005%

    No Known Activations