INDEX

Explanations

specific nouns related to literature and authors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ovich

-0.19

zv

-0.17

aver

-0.17

kv

-0.16

 Shay

-0.16

ayd

-0.16

AVA

-0.16

pv

-0.15

 Royale

-0.15

ayer

-0.15

POSITIVE LOGITS

Jew

0.23

Paw

0.21

jaw

0.21

Sew

0.20

Lew

0.20

wj

0.20

Wor

0.20

elow

0.19

pj

0.19

ds

0.19

Activations Density 0.020%

specific nouns related to literature and authors

No Comments

No Known Activations