INDEX

Explanations

references to literary works, particularly novels and plays

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

wards

-0.18

yor

-0.17

fre

-0.15

heit

-0.15

awai

-0.15

bit

-0.14

sheet

-0.14

edin

-0.14

POSITIVE LOGITS

omain

0.16

 ÄĳÃŃch

0.15

aldo

0.14

æĮº

0.14

ÐºÐ¾ÑĤ

0.14

ijken

0.14

Î¸Î±

0.14

vest

0.14

earch

0.13

-length

0.13

Activations Density 0.023%

references to literary works, particularly novels and plays

No Comments

No Known Activations