INDEX

Explanations

programming-related terminology and syntax elements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ãĥ¼ãĥĲ

-0.16

resco

-0.15

icorn

-0.15

 à¤¹à¤²

-0.15

Ã¢h

-0.15

StackTrace

-0.15

ovit

-0.15

etri

-0.14

grams

-0.14

lad

-0.14

POSITIVE LOGITS

_amp

0.17

WindowSize

0.16

env

0.15

 ÎºÎ¿Î¹

0.14

ÙħÙĬÙĦ

0.14

plain

0.14

ãĥĭãĤ¢

0.14

 celib

0.14

 plain

0.13

 Plain

0.13

Activations Density 0.238%

programming-related terminology and syntax elements

No Comments

No Known Activations