INDEX

Explanations

terms related to deprecated features or components in technology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

thing

-0.16

 Awake

-0.15

ç«ĭãģ¦

-0.15

áº¿

-0.14

rts

-0.14

ixture

-0.14

JKLMNOP

-0.14

rs

-0.13

clide

-0.13

POSITIVE LOGITS

aland

0.20

coni

0.16

plib

0.15

ovo

0.15

UGIN

0.15

å²³

0.15

opol

0.14

UNET

0.14

moz

0.14

 valid

0.14

Activations Density 0.030%

terms related to deprecated features or components in technology

No Comments

No Known Activations