INDEX

Explanations

references to categories and classifications within various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

å¤ªéĥİ

-0.19

otte

-0.16

annis

-0.15

à¸´à¸Ħ

-0.14

illes

-0.13

ãĥĥãĤ·ãĥ¥

-0.13

ongyang

-0.13

anship

-0.13

áº§n

-0.13

lex

-0.13

POSITIVE LOGITS

 category

0.60

 categories

0.51

 Category

0.47

category

0.46

-category

0.44

Category

0.44

 Categories

0.42

 CATEGORY

0.41

 ÐºÐ°ÑĤÐµÐ³Ð¾ÑĢ

0.41

categories

0.41

Activations Density 0.085%

references to categories and classifications within various contexts

No Comments

No Known Activations