INDEX

Explanations

references to book publications and their details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

hic

-0.16

alt

-0.15

al

-0.14

ditor

-0.14

letic

-0.14

 isolated

-0.13

ewis

-0.13

isol

-0.13

itz

-0.13

 bottom

-0.13

POSITIVE LOGITS

ENTA

0.20

mutable

0.17

elper

0.15

çŃĳ

0.15

stru

0.15

unsch

0.15

 scaleY

0.15

_locals

0.14

 exem

0.14

 Convers

0.14

Activations Density 0.038%

references to book publications and their details

No Comments

No Known Activations

references to book publications and their details

No Comments

No Known Activations