INDEX

Explanations

references to common practices and experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ondon

-0.16

è²

-0.15

egan

-0.15

à¸Ńà¸Ļ

-0.15

 Ø¨Ø´

-0.14

veis

-0.14

rist

-0.14

à¹Ģà¸ł

-0.14

QueryBuilder

-0.14

-preview

-0.14

POSITIVE LOGITS

0.16

 occurrence

0.16

 fare

0.15

0.14

occ

0.14

 Garner

0.14

âĢĮØªØ±ÛĮÙĨ

0.13

ÑĢÑıÐ´

0.13

Activations Density 0.168%

references to common practices and experiences

No Comments

No Known Activations