INDEX

Explanations

technical terminology related to networking

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

rame

-0.17

och

-0.17

avan

-0.16

atoi

-0.16

anger

-0.15

imas

-0.15

oo

-0.15

isk

-0.14

 Chow

-0.14

oom

-0.14

POSITIVE LOGITS

Mahon

0.18

Canonical

0.15

ilde

0.15

ä½³

0.15

ÑĤÑĢ

0.14

exion

0.14

 Canary

0.14

loub

0.14

aÃ±a

0.14

 speeds

0.14

Activations Density 0.027%

technical terminology related to networking

No Comments

No Known Activations