INDEX

Explanations

references to Android-related terms and permissions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

cus

-0.16

rott

-0.15

ibur

-0.15

DebugEnabled

-0.14

ITT

-0.14

MOOTH

-0.14

 Huffman

-0.13

çİ

-0.13

pper

-0.13

odi

-0.13

POSITIVE LOGITS

platz

0.14

AGED

0.14

utsch

0.14

âĦĸâĦĸ

0.13

[]=$

0.13

*)_

0.13

woke

0.13

 Dixon

0.13

ARB

0.13

bows

0.13

Activations Density 0.008%

references to Android-related terms and permissions

No Comments

No Known Activations