INDEX

Explanations

references to control, ownership, and personal agency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ä¸Ķ

-0.18

 addCriterion

-0.17

setFlash

-0.16

ertain

-0.16

.scalablytyped

-0.15

eker

-0.15

 automatically

-0.15

Ð¾ÑĤÑı

-0.15

 automÃ¡ticamente

-0.14

DisplayName

-0.14

POSITIVE LOGITS

 whatever

0.61

 however

0.58

whatever

0.53

 whichever

0.48

Whatever

0.47

 Whatever

0.47

 wherever

0.45

 whenever

0.39

however

0.38

 However

0.35

Activations Density 0.392%

references to control, ownership, and personal agency

No Comments

No Known Activations