INDEX

Explanations

symbols or characters that may represent formatting or encoding in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 teaching

-0.24

 Teaching

-0.23

 teach

-0.19

-training

-0.18

íĽĪ

-0.17

 Training

-0.17

 instructional

-0.17

 training

-0.17

 programme

-0.17

 Programme

-0.16

POSITIVE LOGITS

 party

0.29

 freshman

0.25

party

0.24

 dorm

0.23

 parties

0.22

 freshmen

0.22

 Party

0.22

 PARTY

0.22

 finals

0.22

-party

0.21

Activations Density 0.015%

symbols or characters that may represent formatting or encoding in the text

No Comments

No Known Activations