INDEX

Explanations

terms related to scientific processes and products

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

Leod

-0.15

abaj

-0.15

 endwhile

-0.15

IDD

-0.14

Ð»Ð°ÑĪ

-0.14

 borderTop

-0.14

ÎµÎ¯

-0.14

amura

-0.14

istica

-0.14

amics

-0.14

POSITIVE LOGITS

ÐĦ

0.15

cab

0.15

arel

0.14

ottle

0.14

jal

0.14

sell

0.14

æ¬ł

0.14

xoops

0.14

yi

0.13

renc

0.13

Activations Density 0.001%

terms related to scientific processes and products

No Comments

No Known Activations