INDEX

Explanations

references to brands and products

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

urg

-0.18

-0.16

 draw

-0.15

posed

-0.15

ÃŃ

-0.15

Âł

-0.15

Sas

-0.14

 intr

-0.14

cl

-0.14

POSITIVE LOGITS

.metamodel

0.16

umont

0.15

èĻİ

0.15

ÐºÑĢÐ°

0.14

ILLISE

0.14

kap

0.14

aters

0.14

xad

0.14

kara

0.14

ibold

0.14

Activations Density 0.075%

references to brands and products

No Comments

No Known Activations