INDEX

Explanations

navigational concepts related to previous and next elements in a list or interface

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

 ?>:</

-0.17

_subplot

-0.16

edBy

-0.15

arsi

-0.15

obile

-0.15

Ã³c

-0.14

arges

-0.14

Ð»ÑıÑħ

-0.14

AREA

-0.13

andle

-0.13

POSITIVE LOGITS

 Prince

0.15

ater

0.14

Prince

0.14

ago

0.14

 travel

0.14

ward

0.14

lun

0.14

ãģ£ãģ±

0.14

rom

0.13

ames

0.13

Activations Density 0.039%

navigational concepts related to previous and next elements in a list or interface

No Comments

No Known Activations