INDEX

Explanations

terms related to examinations and academic assessments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ief

-0.17

ped

-0.16

ria

-0.16

ted

-0.16

-0.15

ment

-0.15

bie

-0.15

tingham

-0.15

err

-0.15

ongs

-0.14

POSITIVE LOGITS

iners

0.33

ining

0.26

INATION

0.25

inati

0.23

ined

0.23

INED

0.22

/test

0.20

-room

0.19

 Prep

0.19

/Test

0.18

Activations Density 0.025%

terms related to examinations and academic assessments

No Comments

No Known Activations