INDEX

Explanations

various ideologies and their implications in socio-political contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ed

-0.19

pad

-0.17

er

-0.16

edar

-0.15

orious

-0.15

ÑģÑı

-0.14

lying

-0.14

pom

-0.14

WISE

-0.14

 lÃ£

-0.14

POSITIVE LOGITS

èĢħçļĦ

0.19

èĢħãģ®

0.18

èĢħ

0.18

-len

0.17

krit

0.17

ophobia

0.16

 itself

0.15

ically

0.15

-lite

0.15

Ø²ÙĬØ¯

0.15

Activations Density 0.069%

various ideologies and their implications in socio-political contexts

No Comments

No Known Activations