INDEX

Explanations

programming code and related syntax elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

enÃ½m

-0.15

ubyte

-0.13

 rather

-0.13

 Gilbert

-0.13

abcdefghijkl

-0.13

á¿¶

-0.13

cctor

-0.13

Picker

-0.12

 unge

-0.12

awner

-0.12

POSITIVE LOGITS

dit

0.25

dit

0.24

Dit

0.19

 likewise

0.17

erno

0.15

lik

0.14

ãĥ¼ãĥĨ

0.14

arg

0.13

 Likewise

0.13

 similarly

0.13

Activations Density 0.660%

programming code and related syntax elements

No Comments

No Known Activations