INDEX

Explanations

references to relocation or changes in residence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

lein

-0.16

ymm

-0.15

Ð¶Ñĥ

-0.15

aire

-0.15

ene

-0.15

juana

-0.14

enes

-0.14

uts

-0.14

rek

-0.14

sthrough

-0.14

POSITIVE LOGITS

 permanently

0.22

Permanent

0.20

 away

0.19

 Permanent

0.19

 permanent

0.18

 perman

0.17

permanent

0.17

 cities

0.17

 into

0.16

Cities

0.16

Activations Density 0.025%

references to relocation or changes in residence

No Comments

No Known Activations