INDEX

Explanations

references to attendance and related identifiers in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

-0.20

 Polic

-0.17

ennen

-0.16

haled

-0.15

 shar

-0.15

 barr

-0.15

illet

-0.14

 alma

-0.14

-strokes

-0.14

-0.13

POSITIVE LOGITS

angkan

0.25

akan

0.22

ang

0.21

angan

0.21

ahan

0.20

arkan

0.19

askan

0.18

unya

0.18

engan

0.18

annya

0.17

Activations Density 0.019%

references to attendance and related identifiers in code

No Comments

No Known Activations