INDEX

Explanations

mentions of media titles or specific video content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

éĢł

-0.15

 ÑģÐ¿Ð¾ÑĢ

-0.15

itou

-0.15

irit

-0.14

âĸį

-0.13

ÑĥÑī

-0.13

ãĤ¿ãĥ«

-0.13

UAL

-0.13

Overview

-0.13

POSITIVE LOGITS

itra

0.14

 substance

0.14

aeper

0.14

 GÃ¼r

0.13

Bre

0.13

AIM

0.13

 newly

0.13

 again

0.13

 payroll

0.13

 Count

0.13

Activations Density 0.019%

mentions of media titles or specific video content

No Comments

No Known Activations