INDEX

Explanations

references to significant life events and personal identities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 Benton

-0.16

 beneficiation

-0.15

Bounding

-0.15

Buf

-0.15

 Banking

-0.15

BUF

-0.14

 Benef

-0.14

 BaseType

-0.14

 Blink

-0.14

 è³

-0.14

POSITIVE LOGITS

 born

0.75

 birth

0.65

 Born

0.62

Born

0.59

çĶŁ

0.59

-born

0.59

born

0.58

birth

0.54

 Birth

0.52

 births

0.47

Activations Density 0.232%

references to significant life events and personal identities

No Comments

No Known Activations