© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 21-LLAMASCOPE-RES-32K
    6. 15105
    Prev
    Next
    INDEX
    Explanations

    geographic locations and community-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TEL
    -0.16
    eros
    -0.15
    å´
    -0.14
     potent
    -0.14
     Gibson
    -0.13
    cret
    -0.13
     Legislature
    -0.13
    .favorite
    -0.13
    quot
    -0.13
     ·
    -0.13
    POSITIVE LOGITS
     town
    0.23
     Grammar
    0.22
    -on
    0.19
     Abbas
    0.19
     Town
    0.18
    -under
    0.18
    pton
    0.18
    shire
    0.17
     RFC
    0.17
    Grammar
    0.16
    Activations Density 0.060%

    No Known Activations