INDEX

Explanations

phrases related to walking and pedestrian activity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

onet

-0.17

-0.16

å¶

-0.15

 Ø§ÙĦØŃÙĦ

-0.14

è½¯

-0.14

áº±m

-0.14

uchi

-0.14

agn

-0.14

kich

-0.13

éĩ

-0.13

POSITIVE LOGITS

bane

0.17

BTN

0.16

 Jacobs

0.15

 Alias

0.15

Alias

0.15

FOX

0.14

:bg

0.14

esson

0.14

isten

0.14

isman

0.14

Activations Density 0.066%

phrases related to walking and pedestrian activity

No Comments

No Known Activations