© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 24-LLAMASCOPE-RES-32K
    6. 19619
    Prev
    Next
    INDEX
    Explanations

    specific names or identifiers often related to individuals or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bast
    -0.16
    CERT
    -0.15
    aille
    -0.15
    ocol
    -0.15
    ovna
    -0.15
    ERRU
    -0.15
    632
    -0.14
    á»Ļc
    -0.14
    ova
    -0.14
    .mem
    -0.14
    POSITIVE LOGITS
     bishop
    0.42
     ep
    0.40
    bishop
    0.37
     Bishop
    0.36
     bishops
    0.36
     arch
    0.33
     cardinal
    0.31
     Prel
    0.29
    ishop
    0.29
     Bis
    0.28
    Activations Density 0.158%

    No Known Activations