INDEX

Explanations

references to awards and recognitions in the context of film and television

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

intel

-0.16

.subscribe

-0.15

Ã¡g

-0.15

 Vide

-0.15

traits

-0.14

apper

-0.14

ãģıãĤĵ

-0.14

ORLD

-0.13

rans

-0.13

lod

-0.13

POSITIVE LOGITS

utura

0.16

ground

0.16

zman

0.15

dep

0.15

.gdx

0.14

plist

0.14

utow

0.14

FTA

0.14

quÃ©

0.14

Activations Density 0.043%

references to awards and recognitions in the context of film and television

No Comments

No Known Activations