INDEX

Explanations

references to recent events or studies

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

tout

-0.16

udoku

-0.15

.mas

-0.15

lectual

-0.14

pecified

-0.14

erial

-0.14

éļ

-0.13

vertise

-0.13

ÅĻiv

-0.13

ÃĥO

-0.13

POSITIVE LOGITS

itto

0.15

esis

0.14

cord

0.14

ekk

0.14

 woll

0.14

 hamm

0.14

afi

0.14

DEX

0.14

Activations Density 0.010%

references to recent events or studies

No Comments

No Known Activations