INDEX

Explanations

expressions of personal feelings and reflections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

åĢ«

-0.15

quia

-0.14

ivirus

-0.14

 unins

-0.14

ezi

-0.14

anders

-0.13

oller

-0.13

nÄħ

-0.13

 Insight

-0.13

deal

-0.13

POSITIVE LOGITS

 hope

0.22

hope

0.20

 Hope

0.19

 hopes

0.18

Hope

0.18

 prive

0.17

 hoping

0.16

hop

0.15

ritt

0.15

HO

0.14

Activations Density 0.116%

expressions of personal feelings and reflections

No Comments

No Known Activations