INDEX

Explanations

occurrences of specific keywords and phrases related to brands and entities in a technological or economic context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

orts

-0.19

iid

-0.17

æĿľ

-0.16

Dup

-0.15

Du

-0.15

ordova

-0.15

Dup

-0.15

ettle

-0.14

 Burton

-0.14

idd

-0.14

POSITIVE LOGITS

ereotype

0.17

hound

0.15

uru

0.15

engkap

0.15

0.14

tha

0.14

 face

0.14

ategorized

0.14

POWER

0.14

 Andersen

0.14

Activations Density 0.020%

occurrences of specific keywords and phrases related to brands and entities in a technological or economic context

No Comments

No Known Activations