INDEX

Explanations

references to popular film and television titles, characters, and their associated elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ifs

-0.14

aml

-0.13

BarItem

-0.13

ItemImage

-0.13

ierz

-0.13

 silence

-0.13

 recovering

-0.13

 connector

-0.13

 value

-0.12

ainer

-0.12

POSITIVE LOGITS

ãĥ¼ãĤº

0.16

 Saga

0.16

&q

0.15

 Overnight

0.15

/Users

0.14

 “âĢ¦

0.14

 "...

0.14

berger

0.14

hoot

0.13

 Part

0.13

Activations Density 0.083%

references to popular film and television titles, characters, and their associated elements

No Comments

No Known Activations