INDEX

Explanations

coding and programming-related structures, particularly brackets and function definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

Äįem

-0.16

 Conf

-0.15

rough

-0.14

ç©´

-0.14

ought

-0.14

 GOODMAN

-0.14

é¬

-0.14

onom

-0.14

leton

-0.14

rection

-0.13

POSITIVE LOGITS

iht

0.18

adden

0.15

adh

0.15

 uninitialized

0.14

upe

0.14

 pale

0.13

RAINT

0.13

 oslo

0.13

istrovstvÃŃ

0.13

veau

0.13

Activations Density 0.018%

coding and programming-related structures, particularly brackets and function definitions

No Comments

No Known Activations