INDEX

Explanations

references to the President and former Presidents, especially in the context of political actions or statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

-0.16

eb

-0.15

uida

-0.13

æľĭ

-0.13

adas

-0.13

sse

-0.13

egie

-0.13

 particular

-0.13

WARN

-0.13

Ì£

-0.13

POSITIVE LOGITS

 Emer

0.19

kee

0.18

íĿ¬

0.15

ÐĴÐ¡

0.14

ango

0.14

fee

0.14

Ã¥r

0.14

ichte

0.14

ain

0.13

 republiky

0.13

Activations Density 0.043%

references to the President and former Presidents, especially in the context of political actions or statements

No Comments

No Known Activations