INDEX

Explanations

references to current events and trending topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

cak

-0.17

udios

-0.16

Ð¾Ð²Ð¸Ñĩ

-0.15

processable

-0.15

atron

-0.15

ttp

-0.14

kie

-0.14

ncia

-0.14

HORT

-0.13

uld

-0.13

POSITIVE LOGITS

 âľĵ

0.18

aman

0.16

0.15

Compare

0.15

dun

0.14

 browse

0.14

ch

0.14

 Gate

0.14

cher

0.14

 PartialView

0.13

Activations Density 0.186%

references to current events and trending topics

No Comments

No Known Activations