© 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. 30-LLAMASCOPE-RES-32K
    11. 11586
    Prev
    Next
    INDEX
    Explanations

    programming-related configuration settings and parameters

    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
     COURT
    -0.20
     Courtney
    -0.20
     court
    -0.20
    Court
    -0.19
     Court
    -0.18
     Cour
    -0.17
    Cour
    -0.17
     courts
    -0.16
     Courts
    -0.16
    -court
    -0.16
    POSITIVE LOGITS
     config
    1.12
    config
    1.01
     Config
    0.99
     configuration
    0.98
    Config
    0.91
     configurations
    0.90
    .config
    0.90
     configs
    0.89
    _config
    0.88
     Configuration
    0.87
    Activations Density 0.218%

    No Known Activations