INDEX

Explanations

phrases that indicate factors or considerations to take into account

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

bler

-0.16

uar

-0.14

otor

-0.14

mana

-0.14

 pert

-0.14

 Elli

-0.14

æĿĲ

-0.14

okoj

-0.14

pert

-0.14

acro

-0.14

POSITIVE LOGITS

ammen

0.16

chod

0.15

è¯¾

0.14

ÃŃÅ¡

0.14

PROPERTY

0.13

iry

0.13

unsch

0.13

ØªÙĥ

0.13

 máº¥t

0.13

èª²

0.13

Activations Density 0.351%

phrases that indicate factors or considerations to take into account

No Comments

No Known Activations