INDEX

Explanations

references to correspondence and historical documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

Fol

-0.14

ç¸

-0.14

ÐµÑı

-0.13

æľĢæĸ°

-0.13

 Breed

-0.13

 folds

-0.13

esz

-0.13

ForResult

-0.13

rum

-0.13

STAT

-0.13

POSITIVE LOGITS

 record

0.19

 Record

0.17

-record

0.17

 preserved

0.17

record

0.16

 records

0.16

 recording

0.16

 ÑģÐ¾Ñħ

0.16

 preserve

0.16

records

0.15

Activations Density 0.113%

references to correspondence and historical documentation

No Comments

No Known Activations