INDEX

Explanations

phrases related to legal disclaimers and warranties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

anner

-0.19

entiful

-0.17

ãĥ¥ãĥ¼

-0.17

èªł

-0.16

acker

-0.16

bose

-0.15

ANNER

-0.15

ackers

-0.15

\grid

-0.14

stoupil

-0.14

POSITIVE LOGITS

igg

0.17

0.16

 Bett

0.15

 Reconstruction

0.15

IFF

0.15

 either

0.15

 Willis

0.14

uno

0.14

agar

0.14

 undo

0.14

Activations Density 0.003%

phrases related to legal disclaimers and warranties

No Comments

No Known Activations