INDEX

Explanations

quantitative descriptions or words indicating superiority and evaluation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

eh

-0.16

 elements

-0.15

 interview

-0.15

 ingredients

-0.15

 barriers

-0.15

 ways

-0.15

 Interview

-0.15

è«¸

-0.14

 survey

-0.14

 interrupt

-0.14

POSITIVE LOGITS

 campaigns

0.25

 hunts

0.24

 searches

0.23

transactions

0.23

projects

0.23

 executions

0.22

 experiments

0.22

Transactions

0.22

 projects

0.22

 purchases

0.22

Activations Density 0.001%

quantitative descriptions or words indicating superiority and evaluation

No Comments

No Known Activations