INDEX

Explanations

references to publication details and bibliographic information

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

mae

-0.17

à¸£à¸§

-0.17

è¦

-0.16

lue

-0.15

æİĴ

-0.14

ricks

-0.14

 Ashe

-0.13

íı

-0.13

ecs

-0.13

ropp

-0.13

POSITIVE LOGITS

æŀļ

0.16

pon

0.16

0.15

Nob

0.14

 Weather

0.14

izador

0.14

erte

0.14

 cherry

0.13

mez

0.13

Activations Density 0.104%

references to publication details and bibliographic information

No Comments

No Known Activations