INDEX

Explanations

words that indicate a sense of annoyance or frustration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

'nin

-0.18

lier

-0.18

beits

-0.17

èĹ

-0.16

bate

-0.16

(s

-0.16

ering

-0.16

reads

-0.16

placer

-0.15

liness

-0.15

POSITIVE LOGITS

(es

0.33

es

0.32

plorer

0.30

tures

0.30

0.29

xed

0.27

perience

0.25

avier

0.24

cellent

0.24

ioms

0.24

Activations Density 0.097%

words that indicate a sense of annoyance or frustration

No Comments

No Known Activations

words that indicate a sense of annoyance or frustration

No Comments

No Known Activations