Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 16-LLAMASCOPE-RES-32K
    6. 6070
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gars
    -0.17
    ̣
    -0.16
     ðŁĺī↵↵
    -0.16
    ertiary
    -0.15
    稿
    -0.14
    indr
    -0.14
    /***/
    -0.14
    Fold
    -0.14
    equip
    -0.14
    akk
    -0.14
    POSITIVE LOGITS
     Crosby
    0.14
     Scient
    0.14
     prosperity
    0.14
    redo
    0.14
     kinda
    0.13
     maybe
    0.13
     Stam
    0.13
     Prosper
    0.13
     bad
    0.13
     sometimes
    0.13
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.