INDEX

Explanations

expressions of humor or sarcasm

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

contr

-0.17

oken

-0.15

apult

-0.15

Slo

-0.15

odka

-0.14

clr

-0.14

ĮĢ

-0.14

anela

-0.14

Ð½Ð¾Ðº

-0.14

Jeg

-0.13

POSITIVE LOGITS

æ£

0.17

 here

0.17

otics

0.17

bitset

0.17

çĴĥ

0.16

_HERE

0.15

udder

0.15

*this

0.15

 Ð·Ð´ÐµÑģÑĮ

0.15

ÑĸÐ»ÑĮ

0.14

Activations Density 0.205%

expressions of humor or sarcasm

No Comments

No Known Activations