INDEX

Explanations

numeric or mathematical terminology related to measurements or evaluations

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

 Sanity

-0.17

combe

-0.16

_compute

-0.15

aille

-0.15

åłĤ

-0.14

 Compute

-0.14

 arguably

-0.14

 compute

-0.14

.compute

-0.13

NullOr

-0.13

POSITIVE LOGITS

âĦĸ

0.21

descr

0.20

 Ñģ

0.20

 âĦĸ

0.19

 standart

0.19

 correspondent

0.18

 Ð¡

0.18

Ukr

0.18

 ÑĢ

0.18

 obligatory

0.18

Activations Density 0.035%

numeric or mathematical terminology related to measurements or evaluations

No Comments

No Known Activations