© 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. 11032
    Prev
    Next
    INDEX
    Explanations

    programming concepts related to data transfer and object handling

    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
    anki
    -0.14
    ViewInit
    -0.14
    mpar
    -0.13
    OptionsResolver
    -0.13
    opt
    -0.13
    otle
    -0.12
    uga
    -0.12
    PFN
    -0.12
     ëĭ¤ìļ´ë°Ľê¸°
    -0.12
    .XtraReports
    -0.12
    POSITIVE LOGITS
     object
    1.30
    object
    1.14
     Object
    1.13
     objects
    1.06
    -object
    1.05
    Object
    1.04
    _object
    0.99
     OBJECT
    0.97
    对象
    0.95
     Objects
    0.94
    Activations Density 0.451%

    No Known Activations