INDEX

Explanations

mentions of television show appearances and roles

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

åĵ

-0.17

èŃľ

-0.15

USTER

-0.15

lymp

-0.15

endon

-0.15

Ì£

-0.14

artz

-0.14

lector

-0.14

issors

-0.14

ipse

-0.13

POSITIVE LOGITS

 roles

0.29

 opposite

0.24

 recurring

0.24

 guest

0.23

 role

0.22

 Guest

0.20

 Roles

0.20

 appearances

0.20

roles

0.20

 appeared

0.20

Activations Density 0.066%

mentions of television show appearances and roles

No Comments

No Known Activations