INDEX

Explanations

conditional statements and logical expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ownik

-0.17

loub

-0.15

ãĥ³ãĥĶ

-0.15

.PERMISSION

-0.14

Ð½ÑĮÐ¾

-0.14

FillColor

-0.14

ga

-0.14

posite

-0.14

à¸Ńà¸ĩà¸Īà¸²à¸ģ

-0.14

Sizer

-0.14

POSITIVE LOGITS

edis

0.15

orne

0.14

ëģ¼

0.14

icari

0.14

jez

0.14

':

0.14

 Turtle

0.14

 Till

0.13

å±

0.13

 demand

0.13

Activations Density 0.108%

conditional statements and logical expressions

No Comments

No Known Activations