INDEX

Explanations

mentions of methods or processes related to problem-solving

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

variably

-0.14

 unfortunate

-0.14

 erst

-0.14

åľ°è¯´

-0.13

 newfound

-0.13

AsString

-0.13

utm

-0.13

licting

-0.13

urdy

-0.13

 Worst

-0.13

POSITIVE LOGITS

 existed

0.21

âĳł

0.18

Statistic

0.17

ï¼Į

0.16

jian

0.16

ï¼ļ↵

0.16

_para

0.15

yun

0.15

ï¼ļ

0.15

Tips

0.15

Activations Density 0.157%

mentions of methods or processes related to problem-solving

No Comments

No Known Activations