INDEX

Explanations

commands and instructions related to device functionality and navigation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

acias

-0.16

 Blowjob

-0.15

_OT

-0.15

aliz

-0.14

Lib

-0.14

ombre

-0.14

.Geometry

-0.14

Bez

-0.14

íĭ

-0.14

iena

-0.14

POSITIVE LOGITS

:Number

0.15

âĨĲ

0.14

 barr

0.14

affer

0.14

boru

0.14

anny

0.14

borne

0.14

 Barr

0.14

 Bend

0.14

į

0.13

Activations Density 0.222%

commands and instructions related to device functionality and navigation

No Comments

No Known Activations