INDEX

Explanations

discussions about audience preferences and community engagement in entertainment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

thren

-0.16

ffen

-0.15

.getProperties

-0.15

igy

-0.14

armor

-0.14

TypeInfo

-0.14

Contract

-0.14

uese

-0.14

oldem

-0.14

rÃ³

-0.13

POSITIVE LOGITS

 physical

0.25

 physically

0.23

 Physical

0.21

physical

0.21

Physical

0.20

 atmosphere

0.16

.face

0.16

 fÃŃs

0.16

 actual

0.16

 face

0.15

Activations Density 0.159%

discussions about audience preferences and community engagement in entertainment

No Comments

No Known Activations