INDEX

Explanations

elements related to arguments, policies, and decision-making processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ochen

-0.17

chs

-0.15

aland

-0.15

chas

-0.14

yl

-0.14

nung

-0.14

 instead

-0.14

 concerned

-0.13

UNCH

-0.13

 tons

-0.13

POSITIVE LOGITS

 someone

0.75

 somebody

0.73

someone

0.71

 Someone

0.63

Someone

0.63

 Somebody

0.56

 alguien

0.54

 jemand

0.52

 something

0.48

something

0.44

Activations Density 0.022%

elements related to arguments, policies, and decision-making processes

No Comments

No Known Activations