© 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. 15-LLAMASCOPE-RES-32K
    11. 26126
    Prev
    Next
    INDEX
    Explanations

    issues related to accountability and communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rout
    -0.17
    arty
    -0.15
    eniz
    -0.14
     excess
    -0.14
    udur
    -0.14
    CustomAttributes
    -0.14
    989
    -0.14
    riv
    -0.14
    .Selenium
    -0.13
    го
    -0.13
    POSITIVE LOGITS
     sensitive
    0.35
    -sensitive
    0.31
     delicate
    0.31
     fragile
    0.27
     sensit
    0.26
     sensitivity
    0.26
    ensitive
    0.25
    æķı
    0.22
    Sensitive
    0.21
     sens
    0.19
    Activations Density 0.328%

    No Known Activations