INDEX

Explanations

mentions of ongoing actions or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ernet

-0.20

azor

-0.17

stra

-0.15

exus

-0.15

aldi

-0.14

acus

-0.14

inte

-0.14

Ä±sÄ±ndan

-0.14

urette

-0.14

states

-0.14

POSITIVE LOGITS

 wrong

0.27

 happen

0.24

 happening

0.23

 bump

0.23

-ons

0.21

 happened

0.20

ons

0.20

wrong

0.19

 down

0.19

 happens

0.19

Activations Density 0.017%

mentions of ongoing actions or events

No Comments

No Known Activations