INDEX

Explanations

rankings and performance comparisons in various contexts

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

Bil

-0.15

andan

-0.15

ysz

-0.15

Ø®ØªÙĩ

-0.14

ilot

-0.14

enson

-0.14

bil

-0.14

à¸Ļà¹Ģà¸ķ

-0.14

bil

-0.14

POSITIVE LOGITS

iping

0.15

Responder

0.15

tach

0.14

asaki

0.14

abcdefgh

0.14

ì°©

0.14

ãģĤãģĴ

0.14

NCY

0.14

tainment

0.13

Activations Density 0.054%

rankings and performance comparisons in various contexts

No Comments

No Known Activations