INDEX

Explanations

references to Jerusalem and related geographical or historical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 arom

-0.16

ut

-0.16

ond

-0.15

lette

-0.15

oco

-0.14

æ²»

-0.14

astes

-0.14

hiba

-0.14

ono

-0.14

awah

-0.14

POSITIVE LOGITS

ormsg

0.18

gend

0.16

pNet

0.15

ASI

0.14

Void

0.14

aled

0.14

ft

0.13

Î»Î¿Î¹

0.13

addin

0.13

asi

0.13

Activations Density 0.011%

references to Jerusalem and related geographical or historical terms

No Comments

No Known Activations