INDEX

Explanations

topics related to political discourse

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

...

-0.21

...

-0.18

 [...]

-0.17

 (...)

-0.17

ãĥ»ãĥ»ãĥ»

-0.16

--

-0.14

 ...↵↵

-0.14

Ã¶rt

-0.14

 Ã¤

-0.14

(...)

-0.14

POSITIVE LOGITS

US

0.17

USA

0.15

 wanna

0.14

USA

0.14

.gdx

0.14

igua

0.14

 either

0.14

my

0.14

 Donald

0.14

 Board

0.14

Activations Density 0.000%

topics related to political discourse

No Comments

No Known Activations