INDEX

Explanations

phrases related to regulations and legislative actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

orton

-0.15

ilit

-0.14

illas

-0.14

IDA

-0.14

iliz

-0.14

otime

-0.13

ŀæĢ§

-0.13

yna

-0.13

kÃ©

-0.13

 possess

-0.13

POSITIVE LOGITS

upp

0.18

PLY

0.16

 vznik

0.15

lopedia

0.14

 TMPro

0.14

 incident

0.14

incident

0.14

pite

0.13

adaki

0.13

esc

0.13

Activations Density 0.058%

phrases related to regulations and legislative actions

No Comments

No Known Activations