INDEX

Explanations

terms and phrases related to future projections and expectations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

munition

-0.15

ØªÙĨ

-0.15

 deck

-0.14

Jug

-0.14

jej

-0.14

ÄĻd

-0.13

ickers

-0.13

ickt

-0.13

itzer

-0.13

/Foundation

-0.13

POSITIVE LOGITS

uish

0.15

rama

0.15

 subs

0.14

 presence

0.14

alsa

0.14

subs

0.14

rah

0.14

sah

0.14

íĴĪ

0.13

deen

0.13

Activations Density 0.003%

terms and phrases related to future projections and expectations

No Comments

No Known Activations