INDEX

Explanations

references to literary works 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 @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

iaux

-0.16

æĢĴ

-0.15

lÄ±ÄŁÄ±na

-0.15

client

-0.15

ijkstra

-0.14

å¤§åħ¨

-0.14

ittel

-0.14

ajs

-0.14

 client

-0.14

mits

-0.14

POSITIVE LOGITS

MLA

0.21

 textual

0.20

 Literary

0.19

 reading

0.19

 literary

0.18

READING

0.18

 readings

0.18

 texts

0.18

 Genre

0.17

 Reception

0.17

Activations Density 0.128%

references to literary works and authors

No Comments

No Known Activations