INDEX

Explanations

phrases indicating speech or communication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

dub

-0.14

ALAR

-0.13

 Ã§evir

-0.13

isdigit

-0.12

ugi

-0.12

translator

-0.12

edl

-0.12

.VisualBasic

-0.12

zeigen

-0.12

POSITIVE LOGITS

 word

1.09

 words

1.09

words

0.91

word

0.91

 WORD

0.89

-word

0.88

 Words

0.85

 Word

0.82

Word

0.80

_word

0.78

Activations Density 0.317%

phrases indicating speech or communication

No Comments

No Known Activations