INDEX

Explanations

expressions of frustration and dissatisfaction with service or products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ÑĦÑĸ

-0.17

Î¸Î·

-0.17

ÑĦÐ¸

-0.16

vÄĽd

-0.15

Ã¡mara

-0.14

utherford

-0.14

Ã©t

-0.14

 Sexe

-0.14

.ba

-0.14

ÑĢÐ°Ðº

-0.14

POSITIVE LOGITS

 rencont

0.15

ember

0.15

ibe

0.13

ibi

0.13

gin

0.13

çĸ

0.13

dz

0.13

uom

0.13

toi

0.13

CBC

0.13

Activations Density 0.009%

expressions of frustration and dissatisfaction with service or products

No Comments

No Known Activations