INDEX

Explanations

instances where the word "leave" is used in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

/from

-0.15

 Yates

-0.14

ithe

-0.14

oka

-0.14

../../../

-0.14

adu

-0.14

mile

-0.14

../../../../

-0.14

mak

-0.14

ERA

-0.13

POSITIVE LOGITS

uracy

0.19

ington

0.17

vens

0.16

velt

0.16

Jesus

0.15

-handed

0.15

ward

0.15

wards

0.15

odes

0.15

Activations Density 0.060%

instances where the word "leave" is used in various contexts

No Comments

No Known Activations