INDEX

Explanations

comparisons or similes

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

ilyn

-0.17

hm

-0.16

Ã¯

-0.16

.ZERO

-0.15

ÙħÙħ

-0.15

UCH

-0.14

ossa

-0.14

-u

-0.14

 cÃ´t

-0.14

POSITIVE LOGITS

imary

0.16

HITE

0.16

anje

0.16

utor

0.15

ington

0.15

allery

0.15

emade

0.15

Pod

0.15

conomy

0.14

ierge

0.14

Activations Density 0.029%

comparisons or similes

No Comments

No Known Activations