INDEX

Explanations

specific morphological patterns or repeated elements in a text, possibly related to grammatical features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ukkit

-0.17

unga

-0.16

(íģ¬ê¸°

-0.15

ustum

-0.15

Ñľ

-0.14

unge

-0.14

(EXPR

-0.14

Ð¿ÑĤÐ¾Ð¼

-0.14

æ®Ĭ

-0.14

@brief

-0.14

POSITIVE LOGITS

kl

0.23

ved

0.23

obi

0.21

hap

0.21

ze

0.20

oÄį

0.20

vel

0.20

tom

0.19

kin

0.19

 ÑģÐºÐ»Ð°Ð´Ñĥ

0.19

Activations Density 0.004%

specific morphological patterns or repeated elements in a text, possibly related to grammatical features

No Comments

No Known Activations