INDEX

Explanations

references to Amazon and its business practices

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

agher

-0.19

insula

-0.16

yre

-0.15

 ÐļÐ°Ð±

-0.14

è§

-0.14

emez

-0.14

aukee

-0.14

etsk

-0.14

ooth

-0.14

POSITIVE LOGITS

 Amazon

0.58

Amazon

0.52

 amazon

0.48

amazon

0.44

.amazon

0.43

 Prime

0.43

AWS

0.42

 Kindle

0.38

Prime

0.36

mazon

0.36

Activations Density 0.050%

references to Amazon and its business practices

No Comments

No Known Activations