INDEX

Explanations

questions reflecting disbelief or challenging established norms

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

ucu

-0.15

acz

-0.14

iw

-0.14

Ð¸Ð½ÐºÐ¸

-0.14

oling

-0.14

itud

-0.13

çłĶç©¶æīĢ

-0.13

 Casc

-0.13

 rÃ³wn

-0.13

.library

-0.13

POSITIVE LOGITS

perf

0.15

æĮ¯

0.15

unf

0.14

assa

0.14

ang

0.14

why

0.14

imations

0.14

SFML

0.13

Activations Density 0.028%

questions reflecting disbelief or challenging established norms

No Comments

No Known Activations