INDEX

Explanations

references to archival collections and manuscripts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

-template

-0.16

Ð¾Ð¿ÑĢÐ¸

-0.15

/template

-0.15

IBC

-0.15

 disease

-0.14

_dev

-0.14

↵

-0.14

iske

-0.14

POSITIVE LOGITS

 collection

0.26

 collections

0.25

archives

0.24

 Collection

0.24

collection

0.24

collections

0.24

 Archives

0.23

 archives

0.23

 digit

0.22

 Archive

0.22

Activations Density 0.086%

references to archival collections and manuscripts

No Comments

No Known Activations