INDEX

Explanations

references to legal and procedural guidelines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

utan

-0.19

ochen

-0.15

ISS

-0.15

 gren

-0.15

angu

-0.15

fn

-0.14

anco

-0.14

 Lodge

-0.14

akh

-0.14

uzz

-0.13

POSITIVE LOGITS

 check

0.25

 consult

0.25

 Check

0.23

check

0.20

Check

0.20

consult

0.20

.check

0.20

 Consult

0.19

Consult

0.19

 please

0.18

Activations Density 0.169%

references to legal and procedural guidelines

No Comments

No Known Activations