INDEX

Explanations

expressions indicating anticipation or planning for future events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ober

-0.18

alic

-0.17

onom

-0.16

elmet

-0.15

ene

-0.15

essler

-0.14

ourn

-0.14

Cmd

-0.13

à¸Ħà¸§

-0.13

vo

-0.13

POSITIVE LOGITS

 promises

0.21

 gonna

0.18

 potentially

0.18

likely

0.17

 likely

0.17

 thÃº

0.16

 promising

0.16

 expect

0.16

opia

0.16

kus

0.16

Activations Density 0.231%

expressions indicating anticipation or planning for future events

No Comments

No Known Activations