INDEX

Explanations

references to high-profile individuals and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

Ã¶tt

-0.16

 Ð¿Ð»Ð¾ÑīÐ°Ð´

-0.15

kak

-0.15

esp

-0.14

Sez

-0.14

bed

-0.14

esa

-0.14

uspended

-0.14

atron

-0.13

 hedge

-0.13

POSITIVE LOGITS

 negatives

0.19

Creator

0.19

ãĤ

0.18

Identifier

0.18

 Creator

0.17

âĪ¨

0.17

 Negative

0.17

 verso

0.17

 negative

0.16

kup

0.16

Activations Density 0.063%

references to high-profile individuals and events

No Comments

No Known Activations