INDEX

Explanations

references to color

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ionage

-0.17

á»ĩnh

-0.15

 spoj

-0.15

usto

-0.14

lund

-0.14

 Kirby

-0.14

ceso

-0.13

closure

-0.13

imon

-0.13

put

-0.13

POSITIVE LOGITS

Ð»ÑİÐ´

0.19

icha

0.16

 scheme

0.15

 Ð½Ð°ÑĢÐ¾Ð´Ñĥ

0.15

å¼

0.14

ArrayOf

0.14

blind

0.14

 Danger

0.14

.serializer

0.14

 Millennium

0.14

Activations Density 0.035%

references to color

No Comments

No Known Activations