INDEX

Explanations

possessive forms related to personal attributes or ownership

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

-0.18

-0.16

-0.15

ino

-0.15

ickle

-0.14

ala

-0.14

ins

-0.14

 acting

-0.14

opal

-0.14

POSITIVE LOGITS

oenix

0.17

 jadx

0.16

 semiclass

0.15

ManagerInterface

0.15

iversite

0.15

RITE

0.14

.parseFloat

0.14

 Hust

0.14

 Mounted

0.14

hue

0.14

Activations Density 0.018%

possessive forms related to personal attributes or ownership

No Comments

No Known Activations