INDEX

Explanations

expressions of dialogue and conversational interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 basically

-0.17

 Basically

-0.17

Basically

-0.16

nay

-0.15

Fuck

-0.15

éĥ

-0.15

fuck

-0.14

huge

-0.14

gm

-0.14

 Fuck

-0.14

POSITIVE LOGITS

 sorter

0.21

 queer

0.18

 arter

0.18

iglia

0.16

 fellows

0.16

couldn

0.15

 positively

0.15

 Jest

0.15

.want

0.14

Que

0.14

Activations Density 0.342%

expressions of dialogue and conversational interactions

No Comments

No Known Activations