INDEX

Explanations

names or references to specific individuals or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

alc

-0.16

 {{--<

-0.16

vap

-0.15

Ø§Ø¦Ø¨

-0.15

 MetroFramework

-0.14

à¸Ħà¸²à¸ª

-0.14

boru

-0.14

 Hedge

-0.14

semb

-0.14

ë¦½

-0.14

POSITIVE LOGITS

--

0.22

—

0.18

0.17

-->

0.15

 moot

0.15

kees

0.15

ï¸ı

0.15

obel

0.14

its

0.14

Activations Density 0.000%

names or references to specific individuals or organizations

No Comments

No Known Activations