INDEX

Explanations

references to performance discussions and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

eil

-0.15

ahlen

-0.15

.predicate

-0.14

TestFixture

-0.14

ãĤĮãģ©

-0.14

Ã¨m

-0.14

æ¦ľ

-0.14

acam

-0.14

eor

-0.14

Ð»ÐµÐ¶

-0.14

POSITIVE LOGITS

 theatre

0.44

 Theatre

0.42

 theater

0.40

 Theater

0.36

 actors

0.36

 productions

0.35

 Actors

0.35

 ÑĤÐµÐ°ÑĤ

0.35

 cast

0.33

 stage

0.33

Activations Density 0.234%

references to performance discussions and events

No Comments

No Known Activations