INDEX

Explanations

numerical data related to area measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ervals

-0.15

essler

-0.15

hread

-0.15

eci

-0.14

oker

-0.14

beits

-0.14

æĪĲäºº

-0.14

åĲĪæł¼

-0.14

ocate

-0.14

 Pron

-0.13

POSITIVE LOGITS

amik

0.17

ikit

0.17

kul

0.16

 æ¾

0.15

ernote

0.15

ÑĸÐ´Ð½Ð¾

0.14

trap

0.14

glas

0.14

 isFirst

0.14

rip

0.14

Activations Density 0.008%

numerical data related to area measurements

No Comments

No Known Activations