INDEX

Explanations

elements related to media and television ratings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 exposures

-0.15

alink

-0.14

 expose

-0.14

ertz

-0.14

_ATTACH

-0.14

 Newsletter

-0.13

_drvdata

-0.13

á»§ng

-0.13

isas

-0.13

 publicity

-0.13

POSITIVE LOGITS

Clip

0.20

optic

0.19

 Clip

0.16

 toast

0.16

 Telephone

0.15

âĢĤ

0.15

.library

0.15

Telephone

0.15

UseProgram

0.15

 Supreme

0.15

Activations Density 0.002%

elements related to media and television ratings

No Comments

No Known Activations