INDEX

Explanations

terms related to postal services and kitchen organization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

rons

-0.17

orig

-0.17

Å©

-0.15

RIPT

-0.15

omi

-0.15

leme

-0.14

_YUV

-0.14

íĮĮ

-0.14

rior

-0.14

href

-0.14

POSITIVE LOGITS

coc

0.19

coc

0.16

ÃŃses

0.15

icari

0.15

ãĥ³ãĥ

0.15

REA

0.14

eldorf

0.14

apg

0.14

antro

0.14

ailable

0.13

Activations Density 0.006%

terms related to postal services and kitchen organization

No Comments

No Known Activations