INDEX

Explanations

phrases that indicate a sequence or progression, particularly involving the word "by."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

_blob

-0.16

abar

-0.15

arella

-0.15

anz

-0.14

urai

-0.14

abel

-0.14

lick

-0.13

ç´ł

-0.13

POSITIVE LOGITS

 Bain

0.16

ÑĢÐ¸Ð¼

0.16

wagon

0.15

»¿

0.15

lain

0.14

wards

0.14

ÎºÏģÎ±

0.14

hangi

0.13

Î®Î½

0.13

bal

0.13

Activations Density 0.080%

phrases that indicate a sequence or progression, particularly involving the word "by."

No Comments

No Known Activations