INDEX

Explanations

legal terminology and framework

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ount

-0.15

olumn

-0.14

atically

-0.14

ito

-0.14

ITO

-0.14

POSITIVE LOGITS

yyn

0.18

ãĥ³ãĥĳ

0.17

avra

0.17

isoft

0.16

",__

0.15

'{@

0.15

erot

0.15

ypse

0.15

unday

0.15

eters

0.15

Activations Density 0.356%

legal terminology and framework

No Comments

No Known Activations