INDEX

Explanations

specific formatting cues and structured data elements in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

tut

-0.15

ll

-0.15

ieux

-0.14

áº¡ng

-0.14

atural

-0.14

otte

-0.14

-0.13

att

-0.13

POSITIVE LOGITS

Boom

0.17

toDouble

0.17

appid

0.15

obot

0.15

hawks

0.15

hawk

0.15

ODB

0.14

 Boom

0.14

vak

0.14

DisplayStyle

0.14

Activations Density 0.004%

specific formatting cues and structured data elements in a document

No Comments

No Known Activations