INDEX

Explanations

proper nouns and specific names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Hob

-0.15

á»¥n

-0.14

Zhu

-0.12

Ø±ÙĪØ¯

-0.12

.zh

-0.11

 Elsa

-0.11

 Tibetan

-0.11

krv

-0.10

ë¶

-0.10

 Spokane

-0.10

POSITIVE LOGITS

Cox

0.69

ox

0.66

ox

0.65

Sax

0.64

CX

0.64

Rex

0.63

Pax

0.62

FX

0.60

 Lexington

0.60

Rox

0.60

Activations Density 1.272%

proper nouns and specific names

No Comments

No Known Activations