INDEX

Explanations

mathematical expressions and notation

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

Ih

-0.16

 Blink

-0.15

/***

-0.14

ettel

-0.14

oks

-0.14

enheim

-0.14

seealso

-0.14

petto

-0.14

antan

-0.13

 ÙĪØ±

-0.13

POSITIVE LOGITS

}_

0.35

}_{

0.28

 club

0.19

}\

0.18

 Club

0.16

inÃ§

0.16

radient

0.16

 CLUB

0.16

}(

0.15

Activations Density 0.109%

mathematical expressions and notation

No Comments

No Known Activations