INDEX

Explanations

references to geographical locations or areas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

agger

-0.17

inja

-0.16

fdc

-0.15

 ÎĶE

-0.15

swer

-0.14

urve

-0.14

ozo

-0.14

á»ĥ

-0.14

á»©

-0.14

urr

-0.14

POSITIVE LOGITS

ãģ°ãģĭãĤĬ

0.16

istrovstvÃŃ

0.16

alet

0.15

 Schro

0.15

CONTACT

0.14

abo

0.14

BS

0.14

tid

0.14

ÏģÎ¿

0.14

æķ·

0.13

Activations Density 0.020%

references to geographical locations or areas

No Comments

No Known Activations