INDEX

Explanations

references to recognition or acknowledgment of individuals and their contributions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 plav

-0.15

iferay

-0.15

elsing

-0.15

Äįe

-0.15

eking

-0.14

nell

-0.14

ÅĽcie

-0.14

uco

-0.14

celand

-0.14

itur

-0.14

POSITIVE LOGITS

arial

0.15

renom

0.14

re

0.14

 Shen

0.14

 directly

0.14

beat

0.14

/xhtml

0.14

 borderTop

0.14

orch

0.14

 Barber

0.14

Activations Density 0.239%

references to recognition or acknowledgment of individuals and their contributions

No Comments

No Known Activations