INDEX

Explanations

mathematical symbols and notation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

rlen

-0.16

Ð»ÑıÐ´

-0.16

-region

-0.14

 McKin

-0.14

urd

-0.14

eler

-0.14

pac

-0.14

éħį

-0.14

eline

-0.14

gos

-0.14

POSITIVE LOGITS

alli

0.15

 submar

0.15

mnop

0.14

å¸Į

0.14

 Rolls

0.14

ilib

0.13

à¸Ļà¸²

0.13

ordable

0.13

empo

0.13

arters

0.13

Activations Density 0.083%

mathematical symbols and notation

No Comments

No Known Activations