INDEX

Explanations

words and phrases related to estimation or approximation of values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

acco

-0.18

Lev

-0.15

povÄĽ

-0.15

 persist

-0.15

sp

-0.15

ilan

-0.14

pyx

-0.14

 casting

-0.14

ekk

-0.14

 Oswald

-0.14

POSITIVE LOGITS

bette

0.18

.infinity

0.16

endor

0.16

:"-

0.15

kola

0.15

ENDOR

0.15

unner

0.15

ìĹ´

0.15

.Elapsed

0.14

ãĥ³ãĥ

0.14

Activations Density 0.129%

words and phrases related to estimation or approximation of values

No Comments

No Known Activations