INDEX

Explanations

terms related to advancing policies, initiatives, or agendas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ptom

-0.19

jo

-0.17

å¿Ĺ

-0.15

tÃŃ

-0.15

Jo

-0.15

issor

-0.15

addy

-0.14

Ð¾Ð»Ñİ

-0.14

.cms

-0.13

/cms

-0.13

POSITIVE LOGITS

csi

0.16

ÐµÑĢÐ±

0.15

vm

0.15

CELER

0.15

bilt

0.15

Å¡ov

0.15

 Tall

0.14

imin

0.14

ets

0.14

csrf

0.14

Activations Density 0.025%

terms related to advancing policies, initiatives, or agendas

No Comments

No Known Activations