INDEX

Explanations

terms related to programming concepts and structures in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

flix

-0.14

yte

-0.14

à¸±à¸Ĺ

-0.13

IALIZ

-0.13

:///

-0.13

/GPL

-0.13

ÙĬØ±Ø§ÙĨ

-0.13

ãģªãģĳãĤĮãģ°

-0.13

ÑĦÐ¸ÑĨÐ¸

-0.13

Ø±Ø¬

-0.13

POSITIVE LOGITS

oux

0.17

 bÃ©

0.15

 recoil

0.14

semb

0.14

ooks

0.14

Ple

0.13

apy

0.13

/tags

0.13

cona

0.13

 elect

0.13

Activations Density 0.311%

terms related to programming concepts and structures in code

No Comments

No Known Activations