INDEX

Explanations

phrases indicating regret or disappointment

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ungs

-0.16

ogie

-0.16

ske

-0.14

alu

-0.14

hv

-0.14

ç°

-0.13

sx

-0.13

Äįen

-0.13

ungan

-0.13

 ØªØŃØµ

-0.13

POSITIVE LOGITS

lesia

0.16

arella

0.16

inski

0.16

ĮĢ

0.16

adows

0.15

fsp

0.15

strup

0.15

.schedulers

0.14

MESS

0.14

Activations Density 0.013%

phrases indicating regret or disappointment

No Comments

No Known Activations