INDEX

Explanations

words related to the Persian culture or identity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

liest

-0.17

ts

-0.15

itore

-0.15

ierz

-0.15

Ð¾Ð¶Ðµ

-0.15

 Shut

-0.15

tes

-0.15

osten

-0.14

èŃ

-0.14

emann

-0.14

POSITIVE LOGITS

pectives

0.27

pective

0.23

pect

0.23

 Pers

0.21

à¤¨à¤²

0.21

HING

0.21

asive

0.20

PECT

0.20

pekt

0.20

 pers

0.20

Activations Density 0.012%

words related to the Persian culture or identity

No Comments

No Known Activations