INDEX

Explanations

phrases indicating a mixture of anticipation and evaluation

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

à¥Įà¤¨

-0.16

fant

-0.15

estruct

-0.14

essor

-0.14

 unnamed

-0.13

cus

-0.13

ãĤ±ãĥĥãĥĪ

-0.13

acios

-0.13

æ¥¼

-0.13

 STDERR

-0.13

POSITIVE LOGITS

ÐļÐ¢

0.17

bable

0.16

0.15

redi

0.15

dbl

0.14

.Magenta

0.14

alon

0.14

Jab

0.14

nila

0.14

 Fowler

0.13

Activations Density 0.338%

phrases indicating a mixture of anticipation and evaluation

No Comments

No Known Activations