INDEX

Explanations

code-related terminology and function definitions in programming contexts

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

íİ

-0.16

Ã©k

-0.14

 Range

-0.14

.Magenta

-0.14

omi

-0.14

Ø¨Ø§ØŃ

-0.13

astro

-0.13

hek

-0.13

WI

-0.13

ãģ¡ãĤī

-0.13

POSITIVE LOGITS

chine

0.18

irie

0.15

vals

0.15

jak

0.14

.habbo

0.14

onen

0.14

_undo

0.14

ÑĩÐ°Ñģ

0.14

kr

0.14

æĺĩ

0.14

Activations Density 0.206%

code-related terminology and function definitions in programming contexts

No Comments

No Known Activations