INDEX

Explanations

references to institutions, events, and prominent figures in culture and history

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ipsis

-0.16

ersiz

-0.15

ynchron

-0.15

gne

-0.15

ÑĢÐ°Ð²Ð¸

-0.14

sil

-0.14

onium

-0.14

uffers

-0.14

unist

-0.13

ansom

-0.13

POSITIVE LOGITS

 White

0.23

White

0.20

.White

0.17

 Whit

0.16

 çĻ½

0.16

Wh

0.16

 Whites

0.16

 WHITE

0.16

_white

0.16

WHITE

0.16

Activations Density 0.018%

references to institutions, events, and prominent figures in culture and history

No Comments

No Known Activations