INDEX

Explanations

geographic locations and cultural landmarks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ÃŃst

-0.16

ENAME

-0.15

Ã¦r

-0.15

ÃŃa

-0.15

.bc

-0.15

qd

-0.15

dou

-0.15

cerr

-0.15

Ã¤m

-0.14

Ã¤r

-0.14

POSITIVE LOGITS

 Hungary

0.50

 Hungarian

0.50

 Budapest

0.49

Hung

0.43

Sz

0.40

 Hung

0.38

Sz

0.36

.hu

0.36

Cs

0.34

Gy

0.32

Activations Density 0.079%

geographic locations and cultural landmarks

No Comments

No Known Activations