INDEX

Explanations

numerical values, particularly those representing dates or statistics

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

ler

-0.16

akov

-0.16

oplayer

-0.16

-0.15

Lis

-0.14

amd

-0.14

 bush

-0.14

ÑĥÐºÐ¸

-0.14

POSITIVE LOGITS

 glyphicon

0.23

0.19

 Obama

0.18

 Obamacare

0.18

 Kinect

0.18

acci

0.17

 Huffington

0.17

 Occupy

0.16

Obama

0.16

doch

0.15

Activations Density 0.113%

numerical values, particularly those representing dates or statistics

No Comments

No Known Activations