INDEX

Explanations

references to time, specifically years and months

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 somehow

-0.17

VERBOSE

-0.15

ted

-0.15

bou

-0.14

iram

-0.14

 stuff

-0.14

.fromString

-0.14

-0.13

ount

-0.13

POSITIVE LOGITS

 dozen

0.24

ìĶ©

0.20

ago

0.18

/stdc

0.17

rade

0.16

 hundred

0.16

rades

0.15

 Ð´ÐµÑģÑıÑĤ

0.15

 thousand

0.15

åĿĽ

0.15

Activations Density 0.063%

references to time, specifically years and months

No Comments

No Known Activations