INDEX

Explanations

instances of humor and social commentary related to personal experiences and notable incidents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

onen

-0.15

 Thousand

-0.15

Hin

-0.15

HU

-0.14

thalm

-0.14

 Hund

-0.14

ÐµÐ½Ð·

-0.14

 differential

-0.13

 collision

-0.13

ctype

-0.13

POSITIVE LOGITS

ehler

0.18

tep

0.16

ngr

0.16

illac

0.15

amac

0.15

ophobia

0.14

 queryInterface

0.14

ire

0.14

eam

0.14

wayne

0.14

Activations Density 0.668%

instances of humor and social commentary related to personal experiences and notable incidents

No Comments

No Known Activations