INDEX

Explanations

statements about notable or historical figures and their accomplishments

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

/is

-0.23

 initially

-0.19

nt

-0.16

 originally

-0.15

 analog

-0.15

-0.14

hausen

-0.14

 recently

-0.13

ãĥĪãĥª

-0.13

POSITIVE LOGITS

now

0.24

 Ø§ÙĦØ¢ÙĨ

0.22

 ÑĤÐµÐ¿ÐµÑĢ

0.21

 ahora

0.20

 remembered

0.20

now

0.19

 maintenant

0.18

 teÄı

0.18

NOW

0.18

credited

0.17

Activations Density 0.345%

statements about notable or historical figures and their accomplishments

No Comments

No Known Activations