INDEX

Explanations

terms related to social groups and relationships among people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

conde

-0.16

oenix

-0.15

áº¯m

-0.15

andle

-0.15

 HÃ¼s

-0.14

fly

-0.14

.people

-0.14

arin

-0.14

wald

-0.14

ÄĽl

-0.14

POSITIVE LOGITS

hood

0.24

ship

0.23

/op

0.22

ships

0.20

rous

0.20

ries

0.20

(s

0.17

chaft

0.17

hip

0.17

/helper

0.17

Activations Density 0.113%

terms related to social groups and relationships among people

No Comments

No Known Activations