INDEX

Explanations

referential phrases regarding location and action in a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ëĿ½

-0.15

 Survivor

-0.15

gaard

-0.14

ÎµÎ¯

-0.14

lady

-0.13

argon

-0.13

 geil

-0.13

xit

-0.13

çļĦè¯Ŀ

-0.13

ock

-0.13

POSITIVE LOGITS

 sint

0.19

 interface

0.19

 sent

0.19

 variable

0.18

API

0.17

 interrog

0.16

 interf

0.16

 funciÃ³n

0.16

Api

0.16

 consulta

0.16

Activations Density 0.018%

referential phrases regarding location and action in a context

No Comments

No Known Activations