© 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. 18686
    Prev
    Next
    INDEX
    Explanations

    references to parent-child relationships in a document structure, likely related to DOM manipulation in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    åĨĨ
    -0.17
    |int
    -0.16
    лага
    -0.16
     mound
    -0.14
     ($)
    -0.14
     withObject
    -0.14
    aku
    -0.14
     Nes
    -0.14
    urm
    -0.14
    ured
    -0.14
    POSITIVE LOGITS
    Opened
    0.15
    elon
    0.15
    idas
    0.15
    idity
    0.15
     Prescription
    0.14
     opened
    0.14
    eh
    0.14
    etak
    0.14
    UniqueId
    0.14
     cr
    0.14
    Activations Density 0.024%

    No Known Activations