INDEX

Explanations

key terms related to roles, characteristics, and elements of storytelling or characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

enos

-0.17

isos

-0.16

ault

-0.16

ersiz

-0.14

eno

-0.14

Ð¾Ð»Ð¾Ñģ

-0.14

ToObject

-0.14

iros

-0.14

AZY

-0.13

iso

-0.13

POSITIVE LOGITS

çļĦæĺ¯

0.25

is

0.23

 adalah

0.18

 include

0.17

å°±æĺ¯

0.17

 consist

0.17

are

0.16

 consists

0.16

æĺ¯ä»Ģä¹Ī

0.16

0.15

Activations Density 0.123%

key terms related to roles, characteristics, and elements of storytelling or characters

No Comments

No Known Activations