INDEX

Explanations

structured date and format patterns

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

-0.15

Dou

-0.15

 Grand

-0.14

eli

-0.14

grand

-0.14

éłĤ

-0.14

elli

-0.14

estre

-0.14

arin

-0.14

_EOF

-0.14

POSITIVE LOGITS

kova

0.17

æĽľæĹ¥

0.16

ptron

0.15

atÃ¼rk

0.15

uka

0.14

ufs

0.14

ORMAT

0.14

|required

0.14

ears

0.14

-dd

0.14

Activations Density 0.005%

structured date and format patterns

No Comments

No Known Activations