INDEX

Explanations

names of locations and historical landmarks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

çĴ

-0.16

BoxLayout

-0.15

PSA

-0.14

 Arist

-0.14

oise

-0.14

roduction

-0.14

sku

-0.14

.trailing

-0.13

CTOR

-0.13

ddd

-0.13

POSITIVE LOGITS

 Vatican

0.25

 Rome

0.24

 Forum

0.22

 Roma

0.21

 Forums

0.20

 Trev

0.20

Forum

0.20

EUR

0.18

Bor

0.18

 Later

0.18

Activations Density 0.076%

names of locations and historical landmarks

No Comments

No Known Activations