INDEX

Explanations

references to memoranda or agreements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ness

-0.17

NESS

-0.16

Ã¹ng

-0.15

icity

-0.15

aa

-0.15

enne

-0.14

wish

-0.14

Î¿ÏĤ

-0.14

th

-0.13

asan

-0.13

POSITIVE LOGITS

abilia

0.35

andum

0.32

ization

0.26

ials

0.24

izing

0.23

ably

0.23

orial

0.22

anda

0.22

izes

0.22

izable

0.22

Activations Density 0.004%

references to memoranda or agreements

No Comments

No Known Activations