INDEX

Explanations

references to literary analysis and historical context within literature

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

Ãºng

-0.16

occo

-0.15

exus

-0.15

æķ·

-0.15

Mess

-0.15

etre

-0.14

ocity

-0.14

anel

-0.14

POSITIVE LOGITS

 Somerset

0.24

 Tennessee

0.21

 Thornton

0.19

 Lager

0.18

CLR

0.17

Kaf

0.17

 Kafka

0.17

 Millet

0.17

 Friedrich

0.17

 Bench

0.16

Activations Density 0.141%

references to literary analysis and historical context within literature

No Comments

No Known Activations