INDEX

Explanations

references and citations in various formats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

-0.18

Ì£

-0.16

etik

-0.16

ec

-0.15

reff

-0.15

pak

-0.15

-0.14

emann

-0.14

POSITIVE LOGITS

 Ð¿ÑĢÐ¸ÑħÐ¾Ð´

0.16

ickt

0.16

rama

0.15

 Ð¶Ðµ

0.14

peq

0.14

ulus

0.14

ocht

0.14

stra

0.14

atform

0.14

strate

0.13

Activations Density 0.004%

references and citations in various formats

No Comments

No Known Activations