INDEX

Explanations

possessive pronouns referencing personal experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

atif

-0.15

owo

-0.14

bane

-0.14

typeid

-0.14

Smarty

-0.14

NavigationBar

-0.14

ocht

-0.14

isses

-0.14

ane

-0.14

imes

-0.14

POSITIVE LOGITS

 visit

0.20

 stay

0.20

 introduction

0.17

 first

0.17

0.16

 Introduced

0.16

 tenure

0.15

 arrival

0.15

 last

0.15

actionDate

0.15

Activations Density 0.112%

possessive pronouns referencing personal experiences

No Comments

No Known Activations