INDEX

Explanations

terms related to computing, technology, and online services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

tuk

-0.16

HasKey

-0.15

canf

-0.15

ouv

-0.14

lops

-0.14

uji

-0.14

.metro

-0.13

/*č↵

-0.13

ike

-0.13

 addCriterion

-0.13

POSITIVE LOGITS

 Bryant

0.15

Ez

0.14

 Cork

0.14

mai

0.14

 Ivory

0.14

spr

0.14

 hypo

0.13

 vets

0.13

linger

0.13

 Keto

0.13

Activations Density 0.109%

terms related to computing, technology, and online services

No Comments

No Known Activations