INDEX

Explanations

instances of the word "this" and other demonstrative pronouns indicating emphasis or importance

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

-0.15

ullo

-0.14

kaar

-0.14

otal

-0.14

 carn

-0.13

ulent

-0.13

 ARGS

-0.13

asant

-0.13

amar

-0.13

POSITIVE LOGITS

à¹Ģà¸Ńà¸ĩ

0.19

#__

0.16

orgia

0.15

å½ĵçĦ¶

0.15

_was

0.15

ãĥ³ãĤ¸

0.14

ohn

0.14

åĽº

0.14

eyim

0.14

swer

0.13

Activations Density 0.114%

instances of the word "this" and other demonstrative pronouns indicating emphasis or importance

No Comments

No Known Activations