INDEX

Explanations

references to archives and archival collections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

etal

-0.16

-template

-0.15

 territory

-0.14

 Brad

-0.14

 disease

-0.14

Ley

-0.14

/template

-0.14

 food

-0.13

 template

-0.13

ÐµÑĢ

-0.13

POSITIVE LOGITS

 Records

0.26

 Papers

0.26

 papers

0.26

 records

0.26

papers

0.24

archives

0.23

Records

0.22

 collection

0.22

records

0.22

documents

0.21

Activations Density 0.119%

references to archives and archival collections

No Comments

No Known Activations

references to archives and archival collections

No Comments

No Known Activations