INDEX

Explanations

mentions of entertainment or media-related content

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

anzi

-0.15

anya

-0.15

dit

-0.15

à¸µà¸¢à¸£

-0.15

ttp

-0.14

adow

-0.14

itta

-0.14

anos

-0.13

ovenant

-0.13

ddit

-0.13

POSITIVE LOGITS

esser

0.17

 Settlement

0.16

HL

0.16

pon

0.15

hab

0.15

 Rath

0.15

iver

0.14

ptions

0.14

ores

0.14

eti

0.14

Activations Density 0.000%

mentions of entertainment or media-related content

No Comments

No Known Activations