© 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. 15-LLAMASCOPE-RES-32K
    11. 24158
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ames
    -0.16
    Ñĥда
    -0.16
    assis
    -0.14
    ادر
    -0.14
    ummy
    -0.14
    itto
    -0.14
    RIES
    -0.14
     shuffle
    -0.14
    iesta
    -0.14
    ries
    -0.14
    POSITIVE LOGITS
    $MESS
    0.16
    ocache
    0.16
     Fibonacci
    0.16
    /Area
    0.15
     Enterprises
    0.15
    Ø®ÙĬ
    0.15
    عر
    0.15
    jours
    0.14
    EMBER
    0.14
     ÑĤабли
    0.14
    Activations Density 0.011%

    No Known Activations