INDEX

Explanations

words related to entertainment or media

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

azo

-0.15

styl

-0.15

apl

-0.14

 Cobra

-0.14

zar

-0.13

 Cobb

-0.13

è¡¡

-0.13

opia

-0.13

POSITIVE LOGITS

isch

0.16

.Parcelable

0.15

isms

0.15

á»Ľi

0.15

ÏĨÎ¹

0.14

.unsplash

0.14

 Sesso

0.14

Sek

0.14

eyse

0.14

ÑĭÑĪ

0.14

Activations Density 0.000%

words related to entertainment or media

No Comments

No Known Activations