INDEX

Explanations

references to high-quality or premium products and services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

anko

-0.18

 Stanley

-0.16

adora

-0.15

icz

-0.14

arr

-0.13

ude

-0.13

ymmetric

-0.13

ê°Ĳ

-0.13

iniz

-0.13

IFA

-0.13

POSITIVE LOGITS

hazi

0.18

cil

0.15

uchs

0.15

ÑĢÐ¸Ñĩ

0.15

ighted

0.15

 gridColumn

0.15

ovol

0.15

ibus

0.14

crast

0.14

_YUV

0.14

Activations Density 0.006%

references to high-quality or premium products and services

No Comments

No Known Activations