INDEX

Explanations

references to restaurants and food-related experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Ð¾Ð½Ð°Ð»ÑĮ

-0.15

LEC

-0.15

UNUSED

-0.15

eus

-0.14

unsch

-0.13

ancia

-0.13

omat

-0.13

ÏģÏĮÏĤ

-0.13

esk

-0.13

meth

-0.13

POSITIVE LOGITS

il

0.19

 Seasons

0.19

 Proof

0.18

 Sidebar

0.18

 Cafe

0.17

 CafÃ©

0.17

 Pane

0.16

 Uncle

0.16

 Java

0.16

 Sticky

0.16

Activations Density 0.079%

references to restaurants and food-related experiences

No Comments

No Known Activations