INDEX

Explanations

references to hard work or efforts made towards achieving a goal

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

atically

-0.16

artner

-0.16

ãĥ¼ãĤº

-0.16

intage

-0.16

datatable

-0.15

eph

-0.15

ìķ¼

-0.15

gether

-0.15

onas

-0.14

gens

-0.14

POSITIVE LOGITS

ening

0.27

ened

0.22

wig

0.19

castle

0.19

-hard

0.18

working

0.17

assing

0.16

ener

0.16

(er

0.15

 fought

0.15

Activations Density 0.027%

references to hard work or efforts made towards achieving a goal

No Comments

No Known Activations