INDEX

Explanations

references to contentious political issues and debates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

gra

-0.15

/popper

-0.14

 vertically

-0.14

ÐµÑĨ

-0.14

pud

-0.14

 Smile

-0.14

 Vall

-0.14

Ã¤ch

-0.14

OUCH

-0.14

oring

-0.13

POSITIVE LOGITS

gif

0.18

gif

0.18

aya

0.17

DAT

0.16

 gifs

0.16

ternet

0.15

 DERP

0.14

ube

0.14

efon

0.14

 shim

0.14

Activations Density 1.038%

references to contentious political issues and debates

No Comments

No Known Activations