INDEX

Explanations

uses of the word "ultimate"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ses

-0.20

thes

-0.18

sel

-0.17

ese

-0.17

emer

-0.17

atori

-0.17

ActionTypes

-0.17

APER

-0.16

thing

-0.15

sg

-0.15

POSITIVE LOGITS

most

0.20

 goal

0.17

atively

0.16

vably

0.16

imate

0.16

ogy

0.16

errupted

0.16

imately

0.16

-final

0.16

 fate

0.15

Activations Density 0.013%

uses of the word "ultimate"

No Comments

No Known Activations