INDEX

Explanations

brand and product names related to consumer goods and features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

argo

-0.15

ulong

-0.14

frog

-0.14

ULONG

-0.14

virt

-0.14

isz

-0.14

 magnesium

-0.14

 gratuiti

-0.14

usat

-0.13

YLE

-0.13

POSITIVE LOGITS

indh

0.15

tep

0.15

ills

0.15

 Nack

0.14

ĮĴ

0.14

aken

0.14

essa

0.14

ãĥ¼ãĥĳãĥ¼

0.13

oldem

0.13

hift

0.13

Activations Density 0.055%

brand and product names related to consumer goods and features

No Comments

No Known Activations