INDEX

Explanations

references to the term "Lincoln" and related phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

-0.15

MBOL

-0.15

engers

-0.15

 láº¡i

-0.15

raquo

-0.14

ei

-0.14

ourced

-0.14

ncia

-0.14

nik

-0.14

QA

-0.14

POSITIVE LOGITS

shire

0.22

coln

0.21

dez

0.16

ette

0.16

cks

0.15

nton

0.15

arity

0.15

de

0.15

acre

0.15

ked

0.14

Activations Density 0.033%

references to the term "Lincoln" and related phrases

No Comments

No Known Activations