INDEX

Explanations

phrases related to scientific explanations and reasoning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

verbatim

-0.16

nga

-0.16

hled

-0.13

 ?>"/>↵

-0.13

keh

-0.13

á»Ļc

-0.13

eling

-0.13

oplan

-0.13

arga

-0.12

voj

-0.12

POSITIVE LOGITS

 explanation

1.13

 explain

1.12

 explanations

1.07

 explaining

1.05

 explains

1.02

 explained

1.00

 Explanation

0.97

 Explain

0.92

explain

0.91

Explanation

0.91

Activations Density 0.288%

phrases related to scientific explanations and reasoning

No Comments

No Known Activations