INDEX

Explanations

keywords and phrases related to online resources and their analytical content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

uga

-0.15

elm

-0.14

arb

-0.14

zag

-0.14

Gr

-0.14

 Rosen

-0.14

Sch

-0.14

ãĥ¼ãĥĸãĥ«

-0.14

ype

-0.14

lsen

-0.13

POSITIVE LOGITS

IDEOS

0.15

ãĥĨãĥ«

0.14

outu

0.14

raid

0.14

rese

0.14

ÑĤÐ¸ÑĢÐ¾Ð²

0.14

.getHeight

0.14

à¤¸à¤°

0.13

/reset

0.13

iliar

0.13

Activations Density 0.000%

keywords and phrases related to online resources and their analytical content

No Comments

No Known Activations