INDEX

Explanations

references to the McDonald's brand or its associated products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

lessly

-0.16

urette

-0.15

 Grill

-0.14

odes

-0.14

 super

-0.14

ank

-0.13

ORA

-0.13

.trailing

-0.13

NSObject

-0.13

 grille

-0.13

POSITIVE LOGITS

iagnostics

0.15

urgeon

0.15

uzzi

0.15

oppins

0.15

iris

0.14

 moÅ¾nÃ¡

0.14

clone

0.14

 witch

0.14

witch

0.14

ugo

0.14

Activations Density 0.004%

references to the McDonald's brand or its associated products

No Comments

No Known Activations