INDEX

Explanations

structured data and relationships within database queries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

elson

-0.19

azi

-0.16

icerca

-0.16

urer

-0.15

omain

-0.15

urum

-0.15

azar

-0.14

gte

-0.14

ARGV

-0.14

’aut

-0.14

POSITIVE LOGITS

Ã¡bado

0.17

 Brid

0.15

odes

0.14

 Eins

0.14

rays

0.14

REE

0.13

_$

0.13

 memcmp

0.13

Bot

0.13

Activations Density 0.546%

structured data and relationships within database queries

No Comments

No Known Activations