INDEX

Explanations

requests or inquiries made by characters in the text

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

inth

-0.20

arel

-0.16

byss

-0.16

inen

-0.15

essed

-0.14

 export

-0.13

riend

-0.13

inan

-0.13

inand

-0.13

RelativeTo

-0.13

POSITIVE LOGITS

era

0.15

;&#

0.15

ìĶ

0.14

ope

0.14

 perk

0.13

 presenter

0.13

/packages

0.13

ewe

0.13

_SCR

0.13

lesen

0.13

Activations Density 0.084%

requests or inquiries made by characters in the text

No Comments

No Known Activations