INDEX

Explanations

programming-related syntax and constructs, particularly in JavaScript

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Suffix

-0.15

ÐĲÑĢÑħÑĸÐ²

-0.14

-0.13

ousel

-0.13

Ale

-0.13

Roe

-0.13

uns

-0.13

dir

-0.12

anel

-0.12

 Lever

-0.12

POSITIVE LOGITS

 pattern

0.29

 Pattern

0.28

pattern

0.26

 patterns

0.24

Pattern

0.24

 Patterns

0.24

Patterns

0.24

 splitting

0.24

patterns

0.24

-pattern

0.24

Activations Density 0.735%

programming-related syntax and constructs, particularly in JavaScript

No Comments

No Known Activations