INDEX

Explanations

question and answer formats about technical support and services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

imens

-0.16

lett

-0.15

agos

-0.15

romo

-0.15

acket

-0.14

ITT

-0.14

 pulses

-0.13

gos

-0.13

 Read

-0.13

SHA

-0.13

POSITIVE LOGITS

can

0.20

Can

0.19

Can

0.17

ORY

0.17

can

0.17

ahun

0.16

my

0.16

ãĢĤæĪĳ

0.15

-can

0.15

engo

0.15

Activations Density 0.030%

question and answer formats about technical support and services

No Comments

No Known Activations