INDEX

Explanations

references to the production and popularity of specific movies or shows

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

credential

-0.15

antity

-0.15

isma

-0.14

YPRE

-0.14

 commun

-0.14

linkplain

-0.14

_FIFO

-0.14

iens

-0.14

çĤī

-0.14

 ÐľÐ¸Ðº

-0.14

POSITIVE LOGITS

 Serial

0.17

 serialization

0.17

 serial

0.16

 slap

0.16

 Agency

0.16

à¸¥à¸°à¸Ħà¸£

0.16

 agency

0.15

 Series

0.15

 historical

0.15

 Historical

0.15

Activations Density 0.099%

references to the production and popularity of specific movies or shows

No Comments

No Known Activations