INDEX

Explanations

terms related to bookings, payments, and policies

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

seek

-0.16

 qual

-0.16

ripe

-0.15

bern

-0.14

 Song

-0.14

ir

-0.14

ch

-0.14

Song

-0.14

aul

-0.14

spo

-0.14

POSITIVE LOGITS

arness

0.16

 Leigh

0.15

Ð»ÐµÐ¹

0.15

akedown

0.15

ìłł

0.15

imei

0.15

/***/

0.14

owell

0.14

Obl

0.14

ÂłPS

0.14

Activations Density 1.242%

terms related to bookings, payments, and policies

No Comments

No Known Activations