INDEX

Explanations

phrases that indicate examples, lists, or specific themes

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

imos

-0.15

="__

-0.14

istrovstvÃŃ

-0.14

anca

-0.13

alles

-0.13

yne

-0.13

ÐµÐ½ÑĤÑĥ

-0.13

 looph

-0.13

unos

-0.13

lag

-0.13

POSITIVE LOGITS

 ways

0.24

 among

0.22

 many

0.20

among

0.19

poss

0.18

 amongst

0.17

 Among

0.17

many

0.17

 Ways

0.17

-many

0.17

Activations Density 0.058%

phrases that indicate examples, lists, or specific themes

No Comments

No Known Activations