INDEX

Explanations

references to legal proceedings and criminal cases

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

MLE

-0.17

amble

-0.15

unker

-0.15

isel

-0.14

Ľ

-0.14

Hos

-0.14

anka

-0.14

orno

-0.14

culus

-0.13

zek

-0.13

POSITIVE LOGITS

ropolis

0.17

attery

0.16

Ð¼ÐµÐ½Ð¸

0.15

Ð¾ÑıÐ½

0.15

 Kauf

0.15

adium

0.15

entiful

0.15

éĨ

0.14

rop

0.14

à¤·

0.14

Activations Density 0.346%

references to legal proceedings and criminal cases

No Comments

No Known Activations