INDEX

Explanations

references to the Massachusetts Institute of Technology (MIT) and its associated programs or contributions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

HING

-0.17

-0.15

ucer

-0.14

Ã¶y

-0.14

.getLocal

-0.14

 worth

-0.14

 utmost

-0.14

cef

-0.14

 nackte

-0.14

ournemouth

-0.14

POSITIVE LOGITS

isko

0.16

MMM

0.15

heet

0.14

ONGL

0.14

odic

0.14

Ð»Ð¸ÑĪ

0.13

ãĥ³ãĥĸ

0.13

Ð½Ð°ÑĢÑĥÐ¶

0.13

Ð²ÐµÑģÑĤÐ¸

0.13

æģĴ

0.13

Activations Density 0.005%

references to the Massachusetts Institute of Technology (MIT) and its associated programs or contributions

No Comments

No Known Activations