INDEX

Explanations

phrases related to educational assessments and their content

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

orges

-0.17

raquo

-0.15

endon

-0.14

zipcode

-0.14

arger

-0.14

ohl

-0.14

istrovstvÃŃ

-0.14

emd

-0.14

ViewById

-0.14

rend

-0.14

POSITIVE LOGITS

 questions

0.29

questions

0.24

 Questions

0.21

_questions

0.19

Questions

0.18

 Fragen

0.18

 question

0.18

 ding

0.15

question

0.15

ingle

0.15

Activations Density 0.027%

phrases related to educational assessments and their content

No Comments

No Known Activations