INDEX

Explanations

proper nouns, particularly names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

awei

-0.15

 éĢ

-0.15

ewater

-0.14

fur

-0.14

forder

-0.14

ProgressBar

-0.14

arnation

-0.14

oupon

-0.14

ideos

-0.13

POSITIVE LOGITS

essler

0.17

ates

0.16

zano

0.16

elle

0.16

izer

0.16

iles

0.15

ite

0.15

Kut

0.15

Ã¸j

0.14

essen

0.14

Activations Density 0.069%

proper nouns, particularly names

No Comments

No Known Activations