INDEX

Explanations

instances of the letter 'A' 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 @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

lee

-0.15

inya

-0.15

ipo

-0.15

Î³Î¿

-0.14

oto

-0.14

fri

-0.14

eldon

-0.14

tic

-0.14

ss

-0.14

POSITIVE LOGITS

emma

0.17

biz

0.16

elman

0.15

REW

0.15

uxtap

0.15

emey

0.15

.AR

0.14

ATIO

0.14

audi

0.14

ATAB

0.14

Activations Density 0.005%

instances of the letter 'A' in various contexts

No Comments

No Known Activations