INDEX

Explanations

specific phrases indicating timing or introductory phrases in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 peri

-0.14

è©

-0.14

eed

-0.14

 phosphate

-0.14

 Bernstein

-0.13

abyrinth

-0.13

oyer

-0.13

 Tang

-0.13

rze

-0.13

.\"

-0.13

POSITIVE LOGITS

Linked

0.15

amac

0.14

à¸´à¸Ļ

0.13

 Chancellor

0.13

andle

0.13

 chancellor

0.13

otch

0.13

 Flat

0.13

atel

0.13

ìĤ´

0.13

Activations Density 0.136%

specific phrases indicating timing or introductory phrases in a narrative context

No Comments

No Known Activations