INDEX

Explanations

phrases indicating possession or association

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

adio

-0.14

ospace

-0.14

oeff

-0.14

 ÙģØ±ÙĪ

-0.14

ahr

-0.13

ech

-0.13

stration

-0.13

Ø²Ø¨

-0.13

onic

-0.13

 Hlav

-0.13

POSITIVE LOGITS

.scalablytyped

0.16

 kalan

0.15

 FetchType

0.15

styl

0.15

iddet

0.14

_compat

0.14

ä¹İ

0.14

ÛĮØ§

0.14

asl

0.14

inkle

0.14

Activations Density 0.008%

phrases indicating possession or association

No Comments

No Known Activations