INDEX

Explanations

geographic locations and addresses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ARAM

-0.17

ouver

-0.15

ë²½

-0.15

Ð°Ð½Ð¸ÑĨ

-0.14

atest

-0.14

iram

-0.14

 Roch

-0.14

lij

-0.14

itas

-0.14

keterangan

-0.14

POSITIVE LOGITS

0.17

0.14

amoto

0.14

 Chap

0.14

Gle

0.13

aint

0.13

urator

0.13

:not

0.13

Activations Density 0.148%

geographic locations and addresses

No Comments

No Known Activations