INDEX

Explanations

references to structured data representation, specifically in tabular formats

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

trimmed

-0.15

 Tween

-0.15

andalone

-0.14

 Humph

-0.14

rÅ¯

-0.14

hip

-0.14

 Hernandez

-0.13

 Sims

-0.13

 worn

-0.13

Tween

-0.13

POSITIVE LOGITS

aras

0.16

Ã§uk

0.15

ar

0.14

ucle

0.14

YNAM

0.14

fir

0.14

adh

0.13

usi

0.13

eni

0.13

 Narr

0.13

Activations Density 0.050%

references to structured data representation, specifically in tabular formats

No Comments

No Known Activations