INDEX

Explanations

specific names and titles related to academic or professional roles

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

askell

-0.18

aks

-0.15

syn

-0.14

 cÃ©lib

-0.14

 Fusion

-0.14

/gcc

-0.13

inae

-0.13

ascar

-0.13

 Erect

-0.13

ollar

-0.13

POSITIVE LOGITS

 preservation

0.32

 Preservation

0.30

 ingest

0.26

 PRES

0.23

 Wayback

0.23

rchive

0.23

Pres

0.23

pres

0.22

 born

0.22

 Preserve

0.21

Activations Density 0.008%

specific names and titles related to academic or professional roles

No Comments

No Known Activations