INDEX

Explanations

technical terms and structures related to programming and computer science concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

é§ħå¾ĴæŃ©

-0.20

ingo

-0.19

querque

-0.17

/copyleft

-0.16

 -*-č↵

-0.16

ï»¿using

-0.16

 ÐµÑģÑĤÐµ

-0.16

 ÑĤÐ°Ð±Ð»Ð¸

-0.16

	TokenName

-0.15

ãĥ»ãĥ»ãĥ»↵↵

-0.15

POSITIVE LOGITS

ENU

0.15

ï¼Įä»¥åıĬ

0.14

0.13

 respectively

0.13

ume

0.12

tit

0.12

Amb

0.12

Tit

0.12

Activations Density 2.816%

technical terms and structures related to programming and computer science concepts

No Comments

No Known Activations