INDEX

Explanations

mentions of communities and places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

åĪĹ

-0.16

lop

-0.15

à¸±à¸¢

-0.15

 Ukra

-0.15

Ð¾Ð´Ð°Ð²

-0.15

Branch

-0.14

 Tent

-0.14

 uninsured

-0.14

_mk

-0.14

">ÃĹ</

-0.13

POSITIVE LOGITS

hall

0.18

wealth

0.18

istrat

0.17

antics

0.16

perature

0.15

semble

0.15

inde

0.15

rophe

0.15

chaft

0.15

imitive

0.15

Activations Density 0.005%

mentions of communities and places

No Comments

No Known Activations