INDEX

Explanations

concepts related to relationships and connections between entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

cape

-0.18

ãĤ¥

-0.17

iness

-0.17

ittel

-0.17

çĲ´

-0.15

shed

-0.15

 ActionTypes

-0.15

endencies

-0.15

.coroutines

-0.15

rah

-0.15

POSITIVE LOGITS

/group

0.17

 with

0.16

ively

0.15

SYM

0.15

unto

0.14

abb

0.14

ally

0.14

 vá»Ľi

0.14

wt

0.13

culate

0.13

Activations Density 0.046%

concepts related to relationships and connections between entities

No Comments

No Known Activations