INDEX

Explanations

affirmations and denials in conversations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 ÑģÐ¾Ð±Ð¾Ð¹

-0.15

ernen

-0.15

alyzed

-0.14

#:

-0.14

metatable

-0.14

gel

-0.14

swick

-0.14

kv

-0.14

 Dense

-0.14

vag

-0.14

POSITIVE LOGITS

/license

0.17

rob

0.15

ÌĢ

0.15

/null

0.15

orus

0.14

arrants

0.14

otropic

0.14

atform

0.13

cono

0.13

okol

0.13

Activations Density 0.046%

affirmations and denials in conversations

No Comments

No Known Activations