INDEX

Explanations

phrases related to expectations and outcomes in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

åī£

-0.15

iet

-0.15

/Internal

-0.14

’ÑıÑĤ

-0.14

è¡

-0.14

æ³³

-0.14

Ø¨ÙĬØ©

-0.13

olatile

-0.13

catalog

-0.13

Åº

-0.13

POSITIVE LOGITS

 happens

0.21

 occurs

0.18

 happen

0.17

 occur

0.15

elen

0.15

 happened

0.15

 exists

0.15

appen

0.15

 comes

0.15

gle

0.15

Activations Density 0.284%

phrases related to expectations and outcomes in various contexts

No Comments

No Known Activations