INDEX

Explanations

keywords related to political decisions and partisan dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

adaki

-0.15

aney

-0.15

-valu

-0.14

.communic

-0.14

Ä±b

-0.14

otas

-0.14

burgh

-0.14

IONS

-0.14

 kÃ¥

-0.14

WORDS

-0.14

POSITIVE LOGITS

 Sens

0.17

 abst

0.17

 votes

0.16

 support

0.15

enza

0.15

 defe

0.15

 Ð¿ÑĢÐ¾Ð³

0.15

 handful

0.14

 override

0.14

 defect

0.14

Activations Density 0.050%

keywords related to political decisions and partisan dynamics

No Comments

No Known Activations