INDEX

Explanations

phrases indicating agreements or relations involving multiple parties

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

 xung

-0.16

Î¿ÏħÎ½

-0.16

/list

-0.14

ITTER

-0.14

APPER

-0.14

/theme

-0.14

 Champions

-0.14

æŃ¯

-0.14

ster

-0.13

elon

-0.13

POSITIVE LOGITS

udeau

0.17

 regards

0.15

 regard

0.15

akash

0.14

aise

0.14

lauf

0.14

onia

0.14

ductive

0.14

ãĤ¹ãĤ¯

0.14

erox

0.14

Activations Density 0.084%

phrases indicating agreements or relations involving multiple parties

No Comments

No Known Activations