INDEX

Explanations

occurrences of the word "at" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

Ð½ÑĸÑĪ

-0.16

iest

-0.16

Ð»Ð¸Ð½Ð°

-0.15

jah

-0.15

owy

-0.15

gee

-0.15

eness

-0.15

äºĭ

-0.14

combe

-0.14

ench

-0.14

POSITIVE LOGITS

 face

0.21

 worse

0.20

 worst

0.20

 best

0.18

 current

0.18

iani

0.17

 FACE

0.16

/accounts

0.15

 present

0.15

.face

0.15

Activations Density 0.051%

occurrences of the word "at" in various contexts

No Comments

No Known Activations