INDEX

Explanations

references to popular TV shows and films

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ectl

-0.17

borough

-0.15

Ã¸re

-0.15

IMA

-0.15

 resources

-0.14

Ð±Ð¸ÑĢÐ°

-0.14

 pillar

-0.14

acha

-0.14

 Chin

-0.14

 carn

-0.14

POSITIVE LOGITS

appl

0.15

æģĴ

0.15

0.14

angle

0.14

-REAL

0.14

illard

0.14

 Ð¿Ð¾ÑĢÑıÐ´

0.14

ampus

0.14

udi

0.13

Activations Density 0.024%

references to popular TV shows and films

No Comments

No Known Activations