INDEX

Explanations

words related to various forms of geographical or societal divisions and classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

berman

-0.16

ulu

-0.16

olver

-0.15

.Ptr

-0.15

bru

-0.15

éĢģæĸĻçĦ¡æĸĻ

-0.14

.Dto

-0.14

Ø§ÙĪÙĬ

-0.14

egas

-0.14

ger

-0.13

POSITIVE LOGITS

alon

0.20

ç½ª

0.15

aign

0.15

Ĥ

0.15

clas

0.14

akash

0.14

unar

0.14

Ø·Ø§ÙĦ

0.13

onden

0.13

Activations Density 0.064%

words related to various forms of geographical or societal divisions and classifications

No Comments

No Known Activations