INDEX

Explanations

references to automotive manufacturing and design

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

aki

-0.19

eva

-0.16

ighbor

-0.15

.Sys

-0.15

omm

-0.15

æľ

-0.15

 Tyson

-0.15

ctl

-0.15

_Parse

-0.14

ê³

-0.14

POSITIVE LOGITS

0.16

0.15

 production

0.15

0.14

 serial

0.14

ibrator

0.14

 dign

0.14

igid

0.14

Production

0.13

Activations Density 0.025%

references to automotive manufacturing and design

No Comments

No Known Activations