INDEX

Explanations

terms related to concepts of technicality and evaluation

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

zw

-0.15

ãĥ¼ãĥŃ

-0.15

inx

-0.14

zi

-0.14

.habbo

-0.14

éłĥ

-0.14

ãĤ¡

-0.14

odb

-0.14

 Lobby

-0.14

åĬĽçļĦ

-0.13

POSITIVE LOGITS

 sense

0.42

sense

0.30

 regard

0.28

 Sense

0.28

 front

0.28

 respect

0.27

 aspect

0.26

 prospective

0.26

 vein

0.25

 terms

0.25

Activations Density 0.061%

terms related to concepts of technicality and evaluation

No Known Activations