INDEX

Explanations

references to travel and tourism activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 Drain

-0.15

 drained

-0.15

 parachute

-0.15

 drain

-0.15

arsi

-0.14

soup

-0.14

_fault

-0.14

 soup

-0.14

fly

-0.14

ledge

-0.13

POSITIVE LOGITS

fer

0.39

 ferry

0.29

Fer

0.28

 crossings

0.26

 Ferry

0.25

 crossing

0.24

fer

0.24

 ferr

0.24

 Crossing

0.23

cross

0.21

Activations Density 0.017%

references to travel and tourism activities

No Comments

No Known Activations