INDEX

Explanations

terms related to programming and technical implementations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 universal

-0.16

ÙĦØ¨

-0.14

ereotype

-0.14

TableRow

-0.14

 Blasio

-0.14

coma

-0.14

[keys

-0.13

efd

-0.13

atte

-0.13

POSITIVE LOGITS

 Vict

0.20

Å¼e

0.18

 Corpor

0.17

 Trib

0.16

Sur

0.16

 Soci

0.16

 Muse

0.16

Ven

0.16

 Vill

0.16

 Gener

0.16

Activations Density 0.495%

terms related to programming and technical implementations

No Comments

No Known Activations