INDEX

Explanations

numeric identifiers or codes, particularly in a structured data format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ady

-0.19

áº·

-0.17

 Guth

-0.15

 McCart

-0.14

eny

-0.14

 langs

-0.14

zman

-0.14

ÏĩÎµÎ´ÏĮÎ½

-0.13

ijken

-0.13

POSITIVE LOGITS

XMLElement

0.15

kle

0.15

oyal

0.14

ochond

0.14

jad

0.14

uin

0.14

 Tales

0.14

å²¡

0.14

diet

0.14

udu

0.14

Activations Density 0.024%

numeric identifiers or codes, particularly in a structured data format

No Comments

No Known Activations