INDEX

Explanations

the name "Howard" in various contexts within the text

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

iaux

-0.18

algo

-0.17

 bÃło

-0.16

ombie

-0.15

ek

-0.14

occupied

-0.14

 ë²Īì§¸

-0.14

orro

-0.14

eyJ

-0.14

eko

-0.13

POSITIVE LOGITS

vig

0.15

burg

0.15

da

0.15

ichern

0.15

rous

0.15

çİĩ

0.14

cir

0.14

alamat

0.14

athan

0.14

sville

0.14

Activations Density 0.005%

the name "Howard" in various contexts within the text

No Comments

No Known Activations