INDEX

Explanations

phrases indicating tendencies or likelihoods

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

ambre

-0.15

xCC

-0.14

opot

-0.14

atto

-0.14

á»ĳt

-0.14

otal

-0.14

ÐµÑģÐ¿

-0.14

 Ð²Ð´ÑĢÑĥÐ³

-0.13

ylim

-0.13

ronym

-0.13

POSITIVE LOGITS

bilt

0.16

lero

0.15

eydi

0.15

ceiver

0.14

ahoma

0.14

/feed

0.14

Ø§ÙģØª

0.14

zia

0.14

0.13

chine

0.13

Activations Density 0.023%

phrases indicating tendencies or likelihoods

No Comments

No Known Activations