INDEX

Explanations

terms related to location and positioning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

reno

-0.16

iga

-0.15

inos

-0.15

istra

-0.15

APH

-0.14

prec

-0.14

pole

-0.14

acen

-0.14

amina

-0.13

à¹Īà¸¥à¸°

-0.13

POSITIVE LOGITS

 disp

0.15

Gem

0.15

vet

0.14

Kov

0.14

 centr

0.14

.Info

0.14

irs

0.14

 recipro

0.14

 Ð²Ð¾Ð·Ð²

0.14

 branded

0.13

Activations Density 0.002%

terms related to location and positioning

No Comments

No Known Activations