INDEX

Explanations

references to the name "Gib" or its variations 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 @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

uction

-0.16

lea

-0.15

à¸µà¹Ĥ

-0.14

ifique

-0.14

ÙİØ¯

-0.14

 authDomain

-0.14

nde

-0.14

_stamp

-0.14

ifice

-0.14

haft

-0.13

POSITIVE LOGITS

bons

0.39

bon

0.26

ilter

0.24

bens

0.24

sons

0.23

bard

0.23

bsite

0.23

bson

0.23

eah

0.22

son

0.21

Activations Density 0.003%

references to the name "Gib" or its variations in various contexts

No Comments

No Known Activations