INDEX

Explanations

references to items in a list or array structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

itz

-0.19

ven

-0.16

zeit

-0.15

aver

-0.15

-0.14

ped

-0.14

sing

-0.14

Ð°Ð²Ð¸

-0.14

OMB

-0.14

icut

-0.14

POSITIVE LOGITS

Ã¼b

0.20

errupted

0.19

ERRU

0.18

getter

0.17

ennon

0.16

ÑĢÐ°Ð·Ñĥ

0.16

raÅ¾

0.15

esseract

0.15

zl

0.15

è´¨

0.14

Activations Density 0.035%

references to items in a list or array structure

No Comments

No Known Activations