INDEX

Explanations

technical terms related to data handling and programming structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

XmlAttribute

-0.16

zÃŃ

-0.15

azÄĥ

-0.14

ãĥ³ãĤ¸

-0.14

duce

-0.14

æķ

-0.14

cak

-0.14

isLoggedIn

-0.14

 Kraft

-0.14

bash

-0.14

POSITIVE LOGITS

.dataTables

0.17

 DataTable

0.17

USD

0.16

ssp

0.16

.caption

0.15

 Material

0.15

tfoot

0.15

 aria

0.14

_material

0.14

RowCount

0.14

Activations Density 0.012%

technical terms related to data handling and programming structures

No Comments

No Known Activations