INDEX

Explanations

articles and positive adjectives preceding nouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

vens

-0.18

contro

-0.16

ÙĨØ³

-0.16

omer

-0.15

bid

-0.15

OKIE

-0.15

leans

-0.15

ads

-0.15

odore

-0.15

opy

-0.14

POSITIVE LOGITS

 recent

0.25

 good

0.20

 curs

0.18

 Recent

0.17

 majority

0.17

recent

0.17

 recently

0.17

 lack

0.16

 person

0.16

 major

0.16

Activations Density 0.217%

articles and positive adjectives preceding nouns

No Comments

No Known Activations