INDEX

Explanations

function definitions and method calls related to data manipulation in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

bil

-0.15

azar

-0.14

sin

-0.14

.TryParse

-0.14

Parser

-0.14

 Parser

-0.13

.parseInt

-0.13

parser

-0.13

 exclusive

-0.13

Sin

-0.13

POSITIVE LOGITS

Pretty

0.40

 Pretty

0.40

pretty

0.39

 toString

0.39

ToString

0.39

toString

0.38

 pretty

0.38

 ToString

0.35

.toString

0.32

.ToString

0.32

Activations Density 0.122%

function definitions and method calls related to data manipulation in code

No Comments

No Known Activations