INDEX

Explanations

elements and attributes commonly used in programming or coding contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

.ov

-0.17

owie

-0.15

ÅĤÄħ

-0.14

itag

-0.14

kke

-0.14

 Microsystems

-0.14

zier

-0.13

egg

-0.13

#:

-0.13

Ð±Ð°

-0.13

POSITIVE LOGITS

Ø¯Ø§ÙĨ

0.16

Pri

0.15

graf

0.15

irit

0.15

 Sand

0.14

rium

0.14

rint

0.14

oir

0.13

chi

0.13

 Daniel

0.13

Activations Density 0.107%

elements and attributes commonly used in programming or coding contexts

No Comments

No Known Activations