INDEX

Explanations

phrases indicating possession or belonging

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

ign

-0.16

 foreign

-0.16

ino

-0.16

wiki

-0.15

org

-0.15

inos

-0.15

lip

-0.15

 Foreign

-0.14

esome

-0.14

POSITIVE LOGITS

OOM

0.17

abra

0.16

legg

0.15

,application

0.14

itag

0.14

ÐµÐ¶

0.14

jong

0.14

yonel

0.14

pper

0.14

.googleapis

0.14

Activations Density 0.003%

phrases indicating possession or belonging

No Comments

No Known Activations