Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 28-LLAMASCOPE-RES-32K
    6. 20936
    Prev
    Next
    INDEX
    Explanations

    references to moral and ethical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æŃ©
    -0.16
    اÙĪØ±ÛĮ
    -0.16
    éĹ´
    -0.15
    ìŀĶ
    -0.15
    247
    -0.15
     morality
    -0.15
     morals
    -0.15
    eldon
    -0.15
    essional
    -0.15
    .flash
    -0.15
    POSITIVE LOGITS
    izing
    0.28
     fiber
    0.25
    istic
    0.24
    ities
    0.23
     fibre
    0.22
     compass
    0.22
    ising
    0.21
     Fiber
    0.21
     relativ
    0.20
    ize
    0.20
    Activations Density 0.016%

    No Known Activations