INDEX

Explanations

keywords and concepts relevant to programming and class definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

es

-0.15

oub

-0.14

ar

-0.14

ois

-0.14

ante

-0.14

ess

-0.14

https

-0.14

emble

-0.13

dum

-0.13

ht

-0.13

POSITIVE LOGITS

Ä°Y

0.16

atatype

0.14

ropa

0.14

 ç§ĭ

0.14

igon

0.14

:convert

0.14

bou

0.14

Ã¤ft

0.14

pard

0.13

à¤Ĥà¤ľ

0.13

Activations Density 0.029%

keywords and concepts relevant to programming and class definitions

No Comments

No Known Activations