INDEX

Explanations

rhetorical questions and expressions of uncertainty or complexity in situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

gether

-0.15

sector

-0.14

 sáº¯c

-0.14

Restr

-0.13

èŃ·

-0.13

achte

-0.13

Ð½Ð¸ÑģÑĤ

-0.13

ctr

-0.13

ality

-0.13

ALS

-0.13

POSITIVE LOGITS

iken

0.17

.scalablytyped

0.15

ofire

0.15

abay

0.15

 martin

0.15

etz

0.14

Ĥ

0.14

RuntimeException

0.14

.gg

0.14

oltage

0.14

Activations Density 1.315%

rhetorical questions and expressions of uncertainty or complexity in situations

No Comments

No Known Activations