INDEX

Explanations

references to interconnectedness and relational dynamics within contexts

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

undle

-0.15

extras

-0.14

itar

-0.14

/tutorial

-0.14

xED

-0.14

owie

-0.13

Ð²ÐµÑĤ

-0.13

 Bart

-0.13

ranges

-0.13

iasi

-0.13

POSITIVE LOGITS

quette

0.16

0.15

å£

0.15

ORY

0.15

nts

0.14

pson

0.14

 interest

0.14

 Kens

0.14

achen

0.14

 Medicine

0.14

Activations Density 0.079%

references to interconnectedness and relational dynamics within contexts

No Comments

No Known Activations