INDEX

Explanations

references to Android package files and related syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

brand

-0.17

Brand

-0.16

 Pants

-0.15

FTER

-0.15

 brand

-0.15

eries

-0.14

hur

-0.14

uzz

-0.14

resse

-0.14

 Lans

-0.14

POSITIVE LOGITS

oltip

0.18

sic

0.15

 Willis

0.14

ç¦®

0.14

sets

0.14

 sieve

0.14

sob

0.14

ohan

0.14

ANDLE

0.14

ausible

0.14

Activations Density 0.002%

references to Android package files and related syntax

No Comments

No Known Activations