INDEX

Explanations

references to academic degrees, specifically doctoral qualifications

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

uci

-0.17

ihan

-0.16

Ð½ÑĸÐ²

-0.15

agu

-0.15

Tier

-0.15

ems

-0.14

rop

-0.14

è§Ĵ

-0.14

agli

-0.14

ened

-0.14

POSITIVE LOGITS

ate

0.22

ates

0.19

alion

0.18

ATES

0.17

ial

0.17

ado

0.16

 Strange

0.15

 Doctor

0.15

 appointment

0.15

AGON

0.15

Activations Density 0.014%

references to academic degrees, specifically doctoral qualifications

No Comments

No Known Activations