INDEX

Explanations

references to product effectiveness and safety

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

Gio

-0.15

hl

-0.14

 catch

-0.14

ivet

-0.14

 Kelly

-0.14

ne

-0.14

gle

-0.14

pon

-0.14

 shift

-0.14

POSITIVE LOGITS

ureau

0.16

æ¼«

0.15

atte

0.15

atten

0.15

 áº¤

0.15

andest

0.15

egend

0.14

erli

0.14

æ½®

0.14

 Sudoku

0.14

Activations Density 0.004%

references to product effectiveness and safety

No Comments

No Known Activations