INDEX

Explanations

calls to action or links for further information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

etal

-0.16

lili

-0.16

åĪ¶

-0.15

reen

-0.15

ill

-0.15

resher

-0.14

agt

-0.14

.bz

-0.14

reff

-0.14

avern

-0.14

POSITIVE LOGITS

 about

0.16

about

0.15

 Eigen

0.15

 rodin

0.15

anes

0.14

çº

0.14

 uninitialized

0.14

LayoutPanel

0.14

thumbnails

0.14

lev

0.14

Activations Density 0.013%

calls to action or links for further information

No Comments

No Known Activations