© 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. 19-LLAMASCOPE-RES-32K
    6. 26376
    Prev
    Next
    INDEX
    Explanations

    words associated with taking, possession, and actions of acquiring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ckt
    -0.19
    itori
    -0.17
    _fonts
    -0.14
    alking
    -0.14
    enis
    -0.14
    ochen
    -0.14
    Disposable
    -0.14
    оÑīи
    -0.14
     Poster
    -0.13
    eten
    -0.13
    POSITIVE LOGITS
     responsibility
    0.17
     ÑĥÑĩаÑģÑĤÑĮ
    0.17
     partido
    0.17
    太éĥİ
    0.17
    StartPosition
    0.16
     grip
    0.15
     initiative
    0.15
    readcr
    0.15
     contacto
    0.14
    respons
    0.14
    Activations Density 0.051%

    No Known Activations