INDEX

Explanations

positive feedback and encouragement regarding performance or skills

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

esda

-0.17

iedy

-0.15

rum

-0.15

estre

-0.14

ornings

-0.14

ornado

-0.14

chant

-0.14

wake

-0.14

lea

-0.13

gatsby

-0.13

POSITIVE LOGITS

 Nice

0.24

 nice

0.23

Nic

0.23

 nicely

0.21

Nice

0.20

 overall

0.18

nice

0.17

 Overall

0.16

 your

0.15

nic

0.15

Activations Density 0.047%

positive feedback and encouragement regarding performance or skills

No Comments

No Known Activations