INDEX

Explanations

phrases related to titles of authority, particularly emphasizing the term "vice president."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

adow

-0.18

breadcrumb

-0.16

 Minute

-0.15

mk

-0.15

Î¬ÏĤ

-0.15

uddy

-0.14

åĪ¶

-0.14

ocy

-0.14

zug

-0.14

áº¡

-0.13

POSITIVE LOGITS

-president

0.31

pres

0.28

 versa

0.28

-President

0.28

 president

0.27

 President

0.27

-pres

0.26

_pres

0.25

-chair

0.25

President

0.23

Activations Density 0.008%

phrases related to titles of authority, particularly emphasizing the term "vice president."

No Comments

No Known Activations