INDEX

Explanations

references to unnecessary or problematic expenditures and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

eki

-0.16

ahrain

-0.16

ubb

-0.15

-0.14

iek

-0.14

ãĥ³ãĥ

-0.14

lse

-0.14

hle

-0.14

 æ³

-0.14

rong

-0.14

POSITIVE LOGITS

 needs

0.39

 needed

0.38

 need

0.36

needs

0.35

need

0.35

 Needed

0.33

needed

0.33

 Needs

0.33

 NEED

0.31

éľĢè¦ģ

0.31

Activations Density 0.194%

references to unnecessary or problematic expenditures and their implications

No Comments

No Known Activations