INDEX

Explanations

dialogues or conversational phrases that express uncertainty 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 @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

veau

-0.17

rott

-0.15

BOSE

-0.15

@qq

-0.15

celik

-0.15

erre

-0.15

ufe

-0.14

.Compile

-0.14

anzi

-0.14

Ã¼f

-0.14

POSITIVE LOGITS

iferay

0.14

 Adler

0.14

 ready

0.14

Jew

0.14

 holy

0.14

contest

0.14

 back

0.14

ocker

0.14

dis

0.13

 both

0.13

Activations Density 0.325%

dialogues or conversational phrases that express uncertainty or questioning

No Comments

No Known Activations