INDEX

Explanations

temporal references, focusing on durations and specific time frames

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

iaux

-0.19

anza

-0.18

Ð»ÑıÐ½

-0.18

mÃŃ

-0.17

rupt

-0.15

curacy

-0.15

oret

-0.15

polator

-0.15

iaz

-0.14

æ®Ĭ

-0.14

POSITIVE LOGITS

itch

0.16

inged

0.15

IDEOS

0.15

_proto

0.14

Eld

0.14

Liver

0.13

 Enumerator

0.13

 Drone

0.13

oz

0.13

ä»

0.13

Activations Density 0.060%

temporal references, focusing on durations and specific time frames

No Comments

No Known Activations