INDEX

Explanations

mathematical notation and formatting in equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

Ari

-0.16

åı²

-0.15

@js

-0.14

ourg

-0.14

ogn

-0.14

_REFER

-0.14

onor

-0.14

ÏģÎ¿

-0.13

-cols

-0.13

 ÐĴÐµÐ»Ð¸

-0.13

POSITIVE LOGITS

.Sdk

0.16

aten

0.15

 Snowden

0.14

 Scho

0.14

thus

0.14

oldem

0.14

Ð»Ð¾Ñĩ

0.14

 Bonds

0.13

Activations Density 0.068%

mathematical notation and formatting in equations

No Comments

No Known Activations