INDEX

Explanations

acronyms and abbreviations related to organizations or technical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 '\''

-0.15

ÇĲ

-0.15

anye

-0.14

MBED

-0.14

loquent

-0.14

uish

-0.14

 Bian

-0.13

ossa

-0.13

 somehow

-0.13

OOK

-0.13

POSITIVE LOGITS

 hence

0.16

eid

0.16

)/

0.14

atron

0.14

anzeigen

0.14

ÑĩÐµÑģÑĤÐ²Ð°

0.14

 Hence

0.14

here

0.13

thic

0.13

Activations Density 0.066%

acronyms and abbreviations related to organizations or technical terms

No Comments

No Known Activations