INDEX

Explanations

phrases related to questions or questioning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

icine

-0.16

uation

-0.16

ummings

-0.16

ication

-0.15

kker

-0.15

temp

-0.15

.tell

-0.14

usion

-0.14

ration

-0.14

orta

-0.14

POSITIVE LOGITS

naires

0.34

naire

0.31

aire

0.24

stellung

0.19

stell

0.17

aires

0.17

stown

0.16

-answer

0.15

rcode

0.15

ÑĭÑģ

0.15

Activations Density 0.059%

phrases related to questions or questioning

No Comments

No Known Activations