INDEX

Explanations

symbols and formatting characters

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

plx

-0.19

ptype

-0.17

baugh

-0.17

charger

-0.15

endimento

-0.15

lio

-0.14

ndl

-0.14

Ð¾Ð±Ð°

-0.14

_CONFIGURATION

-0.14

 **)&

-0.14

POSITIVE LOGITS

 tiny

0.20

 physical

0.20

 small

0.20

 Physical

0.20

 micro

0.17

 tubes

0.17

Physical

0.16

tub

0.16

 Front

0.16

 mini

0.16

Activations Density 0.008%

symbols and formatting characters

No Comments

No Known Activations