INDEX

Explanations

references to nostalgia or looking back at the past

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

 belie

-0.16

Fu

-0.16

ÙİØŃ

-0.15

bout

-0.15

Ã¤ng

-0.14

stad

-0.14

urator

-0.14

ØŃØ¯

-0.14

erdem

-0.14

ollen

-0.14

POSITIVE LOGITS

 Mort

0.15

crement

0.15

ogi

0.15

uga

0.14

ç½²

0.14

fgang

0.14

(åľŁ

0.14

Brains

0.14

cido

0.13

Activations Density 0.199%

references to nostalgia or looking back at the past

No Comments

No Known Activations