© 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. 8-LLAMASCOPE-RES-32K
    11. 24855
    Prev
    Next
    INDEX
    Explanations

    terms related to legal defense and the act of defending oneself or others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Palest
    -0.17
    itoris
    -0.16
    reo
    -0.15
    tes
    -0.15
    //{{
    -0.15
    lh
    -0.15
    culate
    -0.15
    бав
    -0.15
    à¤ł
    -0.15
    heid
    -0.15
    POSITIVE LOGITS
    ably
    0.18
    essel
    0.18
     against
    0.17
    898
    0.17
    ÛĮÙĩ
    0.16
    nÃŃ
    0.16
    893
    0.15
    503
    0.15
    initely
    0.15
    ence
    0.15
    Activations Density 0.042%

    No Known Activations