INDEX

Explanations

phrases related to programming logic and error handling

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

orthy

-0.16

-Ñı

-0.15

sep

-0.15

unn

-0.14

into

-0.14

á»£

-0.14

adies

-0.13

)?$

-0.13

aster

-0.13

alt

-0.13

POSITIVE LOGITS

benh

0.17

å±¥

0.17

 unspecified

0.16

/compiler

0.15

 Watkins

0.15

anje

0.14

 Guarantee

0.14

ĸ

0.14

å¹¸

0.14

elen

0.14

Activations Density 0.006%

phrases related to programming logic and error handling

No Known Activations