© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 28-LLAMASCOPE-RES-32K
    11. 29603
    Prev
    Next
    INDEX
    Explanations

    concepts related to parenting and family dynamics

    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
     mama
    -0.26
     Mom
    -0.26
     parents
    -0.25
     moms
    -0.25
     mommy
    -0.25
     Parents
    -0.24
     mãe
    -0.23
     Mum
    -0.23
     mom
    -0.23
     mamma
    -0.22
    POSITIVE LOGITS
     extended
    0.26
    guard
    0.25
    -guard
    0.25
     guardians
    0.25
    Guard
    0.24
     gran
    0.23
    extended
    0.22
     Extended
    0.22
    Extended
    0.22
     grand
    0.22
    Activations Density 0.062%

    No Known Activations