© 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. 7-LLAMASCOPE-RES-32K
    11. 20407
    Prev
    Next
    INDEX
    Explanations

    phrases related to authority and compliance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itemprop
    -0.16
    BITS
    -0.16
    SPA
    -0.15
    illon
    -0.15
    spa
    -0.15
    osta
    -0.15
    ese
    -0.15
    forman
    -0.15
    -Clause
    -0.14
    kelig
    -0.14
    POSITIVE LOGITS
     Gent
    0.17
    anka
    0.17
     authority
    0.16
    åĿĬ
    0.15
    ÑĢÑĥб
    0.15
    gent
    0.15
    wil
    0.15
    ught
    0.14
     orders
    0.14
    rial
    0.14
    Activations Density 0.443%

    No Known Activations