INDEX

Explanations

proper nouns and significant names or titles

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

 repl

-0.15

adaki

-0.14

orraine

-0.13

.rev

-0.13

 VALID

-0.13

xDA

-0.13

 '".$_

-0.13

iform

-0.13

 multif

-0.13

anness

-0.13

POSITIVE LOGITS

pty

0.17

setattr

0.15

Ach

0.14

zik

0.14

ItemType

0.14

Ã§uk

0.14

SourceType

0.14

 action

0.14

ONTAL

0.13

verter

0.13

Activations Density 0.076%

proper nouns and significant names or titles

No Comments

No Known Activations