INDEX

Explanations

titles of books and references to literary works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

oder

-0.17

 Lucas

-0.16

utzer

-0.15

ade

-0.15

ceph

-0.14

Ð½Ð¸ÑĤ

-0.14

gam

-0.13

pul

-0.13

 rotary

-0.13

chars

-0.13

POSITIVE LOGITS

åĩĨ

0.15

viso

0.15

egen

0.15

IGHL

0.15

å¸¯

0.14

avia

0.14

Ð±ÑĥÐ´ÑĮ

0.14

-Cs

0.14

GES

0.14

(/^\

0.14

Activations Density 0.549%

titles of books and references to literary works

No Comments

No Known Activations