INDEX

Explanations

references to unique identifiers and data organization in a structured format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

orr

-0.14

 values

-0.14

 various

-0.14

cott

-0.14

ahas

-0.14

 tips

-0.14

sl

-0.14

IDs

-0.13

ds

-0.13

POSITIVE LOGITS

 item

0.35

 piece

0.32

 element

0.23

item

0.23

 molecule

0.23

 Piece

0.22

piece

0.22

 ITEM

0.20

_piece

0.20

 Item

0.19

Activations Density 1.197%

references to unique identifiers and data organization in a structured format

No Comments

No Known Activations