INDEX

Explanations

references to purchasing and shopping experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ħn

-0.15

ÐĬ

-0.14

phan

-0.14

Ð°Ð¹Ð´

-0.13

áºŃy

-0.13

æĶĿ

-0.13

eing

-0.13

APER

-0.13

ender

-0.13

rech

-0.13

POSITIVE LOGITS

strtolower

0.14

WAY

0.14

ä»ģ

0.14

 ÑĢÐ°ÑģÑħÐ¾Ð´

0.14

ĥ

0.14

 spree

0.14

linger

0.13

 optarg

0.13

Ú¯ÛĮØ±ÛĮ

0.13

arer

0.13

Activations Density 0.123%

references to purchasing and shopping experiences

No Comments

No Known Activations