INDEX

Explanations

special characters and formatting used in mathematical or formal writing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

gom

-0.16

orda

-0.16

 retr

-0.16

abwe

-0.15

yles

-0.14

ORB

-0.14

chrift

-0.14

Locator

-0.14

cy

-0.14

POSITIVE LOGITS

extView

0.15

olu

0.15

 Mart

0.14

 Stam

0.14

-sidebar

0.14

vely

0.14

 Ð¿ÐµÑĢÐµÐ³

0.14

allet

0.14

ov

0.13

unist

0.13

Activations Density 0.036%

special characters and formatting used in mathematical or formal writing

No Comments

No Known Activations