INDEX

Explanations

locations and geographical names related to various events and contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

iasi

-0.19

evin

-0.14

raman

-0.14

oling

-0.14

Ãªn

-0.14

-0.13

itest

-0.13

ÙĪÙħØ§ÙĨ

-0.13

-Ð´

-0.13

lijah

-0.13

POSITIVE LOGITS

uga

0.16

 à¸Ľà¸£à¸°à¹Ģà¸Ĺà¸¨

0.16

arg

0.16

 marker

0.15

instein

0.14

igue

0.14

 Ø¨ÙĪÙĦ

0.14

ione

0.14

0.13

Activations Density 0.112%

locations and geographical names related to various events and contexts

No Comments

No Known Activations