INDEX

Explanations

geographic and locational information about countries and their features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

midt

-0.17

ukkit

-0.17

midd

-0.16

.central

-0.15

ÐĶÐ°ÑĤÐ°

-0.15

ewe

-0.15

yers

-0.14

 Cove

-0.14

 fitte

-0.14

POSITIVE LOGITS

 shares

0.16

Its

0.15

 Reyn

0.15

 quoi

0.15

via

0.15

its

0.15

 touches

0.15

 neighbors

0.15

 touch

0.15

 borders

0.14

Activations Density 0.034%

geographic and locational information about countries and their features

No Comments

No Known Activations