INDEX

Explanations

references to television networks and programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ollen

-0.16

ooke

-0.15

aper

-0.15

 vars

-0.14

abaj

-0.14

 yans

-0.14

 coin

-0.14

auge

-0.14

_prefs

-0.14

prech

-0.13

POSITIVE LOGITS

 Studios

0.27

-owned

0.22

 studios

0.22

 Pictures

0.21

ictures

0.19

Pictures

0.18

 Networks

0.18

udios

0.17

pictures

0.17

ischer

0.16

Activations Density 0.084%

references to television networks and programming

No Comments

No Known Activations