INDEX

Explanations

names of people and places associated with historical events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

 æĸ

-0.18

iyan

-0.16

ìĻĦ

-0.15

hic

-0.14

ħ

-0.14

/lists

-0.14

AFF

-0.14

Ä¾

-0.13

lett

-0.13

anch

-0.13

POSITIVE LOGITS

chang

0.17

Ãªnh

0.15

ilers

0.14

Triple

0.14

iterr

0.14

itized

0.14

éĿ©

0.14

Ð¼ÐµÐ½Ð°

0.14

zych

0.14

uye

0.14

Activations Density 0.274%

names of people and places associated with historical events

No Comments

No Known Activations