INDEX

Explanations

references to age or generations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

undi

-0.19

baugh

-0.17

allet

-0.16

ential

-0.15

obic

-0.15

xic

-0.15

rescia

-0.15

ELS

-0.14

 Philosophy

-0.14

abb

-0.14

POSITIVE LOGITS

Ø§ÙĨÙĩ

0.16

-wide

0.16

antro

0.15

liness

0.15

/world

0.14

ton

0.14

eton

0.14

ÙĨØ¨

0.14

 pret

0.14

ando

0.14

Activations Density 0.147%

references to age or generations

No Comments

No Known Activations