INDEX

Explanations

elements and features of events or gatherings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

agoon

-0.16

-0.15

ÙĪØ·

-0.14

ãģĿãģĨãģª

-0.14

icode

-0.14

Ð¾ÐºÐ¾Ð½

-0.14

eri

-0.14

/full

-0.13

 Giov

-0.13

ensus

-0.13

POSITIVE LOGITS

ibold

0.23

 latter

0.18

ibal

0.15

urlencode

0.14

INCLUDING

0.14

iek

0.14

ilton

0.14

ikal

0.13

atie

0.13

wei

0.13

Activations Density 0.392%

elements and features of events or gatherings

No Comments

No Known Activations