© 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. 30-LLAMASCOPE-RES-32K
    11. 16569
    Prev
    Next
    INDEX
    Explanations

    elements related to lineage and family connections, particularly in historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fathers
    -0.39
     males
    -0.36
     Fathers
    -0.36
     boys
    -0.35
     guys
    -0.35
     dads
    -0.35
     Boys
    -0.34
    çĶ·æĢ§
    -0.34
     male
    -0.33
     Sons
    -0.33
    POSITIVE LOGITS
     woman
    0.54
     lady
    0.51
    woman
    0.46
     girl
    0.45
     Woman
    0.45
     daughter
    0.42
     female
    0.42
     goddess
    0.41
     Lady
    0.41
     actress
    0.41
    Activations Density 1.210%

    No Known Activations