INDEX

Explanations

numerical references typically associated with scientific articles or publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ssp

-0.14

ael

-0.14

IDAD

-0.14

-txt

-0.13

ServiceProvider

-0.13

/plain

-0.13

athom

-0.13

 plain

-0.13

.GroupLayout

-0.13

plib

-0.13

POSITIVE LOGITS

atz

0.20

arpa

0.17

usat

0.15

amburger

0.15

oug

0.14

upert

0.14

 util

0.14

 invitations

0.14

umpy

0.13

us

0.13

Activations Density 0.016%

numerical references typically associated with scientific articles or publications

No Comments

No Known Activations