INDEX

Explanations

questions and expressions of confusion or misunderstanding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

lech

-0.18

ToBounds

-0.16

ä¹ħ

-0.15

à¤¾à¤¯à¤¨

-0.15

iggs

-0.15

acman

-0.14

Ø¬Ùĩ

-0.14

pective

-0.14

DonaldTrump

-0.14

å°Ĭ

-0.14

POSITIVE LOGITS

why

0.27

why

0.21

Why

0.21

 puzzles

0.18

 puzz

0.18

 puzzle

0.18

Why

0.18

 pourquoi

0.18

 phenomenon

0.17

 mystery

0.17

Activations Density 0.119%

questions and expressions of confusion or misunderstanding

No Comments

No Known Activations