INDEX

Explanations

specific numerical values and their associations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ably

-0.15

 Sass

-0.14

iled

-0.14

elez

-0.14

 Elegant

-0.14

ÑĢÐ¸Ð½

-0.13

ients

-0.13

ublish

-0.13

sep

-0.13

ei

-0.13

POSITIVE LOGITS

 caliber

0.15

icher

0.15

iami

0.15

orre

0.14

ynÄ±

0.14

uye

0.14

unden

0.13

Ð¿ÑĢÐ°

0.13

USA

0.13

andbox

0.13

Activations Density 0.163%

specific numerical values and their associations in various contexts

No Comments

No Known Activations