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

itol

-0.15

sv

-0.14

orgt

-0.14

ahl

-0.14

ths

-0.14

äºŃ

-0.14

chine

-0.14

ØªØ±ÛĮÙĨ

-0.14

ancock

-0.13

 ordinances

-0.13

POSITIVE LOGITS

imbus

0.14

enez

0.14

åı¸

0.14

inscription

0.14

DNA

0.14

bjerg

0.14

avou

0.14

ropy

0.14

ially

0.14

Ø¹Ùĩ

0.14

Activations Density 0.000%

words related to entertainment or media

No Comments

No Known Activations