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. 18-LLAMASCOPE-RES-32K
    6. 28328
    Prev
    Next
    INDEX
    Explanations

    phrases related to emotional states and nuances in social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utzer
    -0.15
    ÃŃst
    -0.15
    averse
    -0.14
    enson
    -0.14
    inx
    -0.14
    üf
    -0.13
    .tif
    -0.13
    uve
    -0.13
    .CV
    -0.12
     definitely
    -0.12
    POSITIVE LOGITS
     resort
    0.35
     instead
    0.35
    åıªèĥ½
    0.33
     Instead
    0.30
    instead
    0.29
    Instead
    0.28
     recourse
    0.27
     alternative
    0.26
     reliance
    0.26
     alternatives
    0.26
    Activations Density 0.334%

    No Known Activations