INDEX

Explanations

elements related to quantified estimates and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

chie

-0.18

.cp

-0.16

.scalablytyped

-0.15

uster

-0.15

DonaldTrump

-0.15

ectar

-0.14

angan

-0.14

igs

-0.14

 cult

-0.13

ones

-0.13

POSITIVE LOGITS

Nh

0.15

orda

0.14

elib

0.14

<Animator

0.14

spring

0.14

Ø®Ø±Ùī

0.14

Ð±ÑĥÐ´

0.14

cil

0.14

eil

0.13

vfs

0.13

Activations Density 0.007%

elements related to quantified estimates and measurements

No Comments

No Known Activations