INDEX

Explanations

words related to government, politics, and public service activities

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

news headlines

np_max-act-logits · claude-4-5-sonnet Triggered by @sripadkarne

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

bro

-0.17

ubber

-0.16

ansi

-0.15

 Jenner

-0.15

íĥĪ

-0.15

 Wich

-0.15

NC

-0.14

NC

-0.14

POSITIVE LOGITS

kah

0.19

IPH

0.16

 Slut

0.16

ante

0.15

 Stad

0.15

 Stuff

0.15

IRON

0.15

uze

0.14

LEM

0.14

ANTE

0.14

Activations Density 0.366%

words related to government, politics, and public service activities

news headlines

No Comments

No Known Activations