INDEX

Explanations

the word "doctor" in various forms and contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

enser

-0.18

Ã©r

-0.16

ichten

-0.15

grav

-0.15

Ã©ro

-0.15

geber

-0.14

punkt

-0.14

uchen

-0.14

ilden

-0.14

gers

-0.14

POSITIVE LOGITS

/ph

0.18

ial

0.18

/engine

0.17

ettle

0.15

ä¿Ĭ

0.15

TestingModule

0.14

<![

0.14

IAL

0.14

ate

0.14

Activations Density 0.034%

the word "doctor" in various forms and contexts

No Comments

No Known Activations