INDEX

Explanations

questions and reasons related to choices and motivations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

bara

-0.17

asa

-0.16

oad

-0.16

aldi

-0.15

ucc

-0.14

uci

-0.14

POSITIVE LOGITS

 chosen

0.29

 chose

0.27

chosen

0.24

 choose

0.21

éĢīæĭ©

0.21

 chois

0.20

_choose

0.20

 choosing

0.20

Choose

0.19

 chooses

0.19

Activations Density 0.129%

questions and reasons related to choices and motivations

No Comments

No Known Activations