INDEX

Explanations

references to elections and voting processes

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

artz

-0.17

ilden

-0.16

elry

-0.16

athers

-0.15

Ð»Ð¸ÑĨ

-0.15

ild

-0.15

yla

-0.15

achat

-0.15

opic

-0.14

uilder

-0.14

POSITIVE LOGITS

eer

0.23

eve

0.19

-winning

0.19

-day

0.18

0.17

 process

0.17

ally

0.16

 Held

0.16

 held

0.15

held

0.15

Activations Density 0.018%

references to elections and voting processes

No Comments

No Known Activations