INDEX

Explanations

references to specific weeks or time periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

osti

-0.18

á»¥

-0.17

abilia

-0.16

eway

-0.15

gings

-0.15

UTO

-0.15

eways

-0.14

ERS

-0.14

 Ging

-0.14

ertools

-0.14

POSITIVE LOGITS

ender

0.30

lys

0.25

ENDER

0.25

-long

0.25

ends

0.25

enders

0.24

åĪĬ

0.24

lies

0.23

ending

0.23

END

0.22

Activations Density 0.014%

references to specific weeks or time periods

No Comments

No Known Activations