INDEX

Explanations

variations of specific German umlauted letters and words associated with the humanities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

nak

-0.17

enic

-0.17

ets

-0.17

oo

-0.17

eda

-0.16

edReader

-0.15

rÃ©

-0.15

able

-0.15

ed

-0.15

eral

-0.15

POSITIVE LOGITS

zung

0.26

igung

0.20

ftar

0.19

nung

0.19

fter

0.18

entlich

0.18

hte

0.18

lung

0.18

fte

0.17

ÃŁ

0.17

Activations Density 0.041%

variations of specific German umlauted letters and words associated with the humanities

No Comments

No Known Activations