INDEX

Explanations

phrases indicating activities or states that are in a state of completion or maximum intensity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

rys

-0.16

addock

-0.15

-wow

-0.15

istically

-0.14

erer

-0.14

tainment

-0.14

coe

-0.14

acht

-0.14

 Scala

-0.14

urm

-0.14

POSITIVE LOGITS

ÐµÐ²Ð¸

0.15

JR

0.15

uss

0.14

ulus

0.14

ĶåĽŀ

0.14

urat

0.14

ÙĩÙĪØ±

0.13

 Covered

0.13

TS

0.13

Activations Density 0.006%

phrases indicating activities or states that are in a state of completion or maximum intensity

No Comments

No Known Activations