INDEX

Explanations

the name "Marion" and variations of its suffixes or forms

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

vel

-0.15

ÅĻeh

-0.15

Vel

-0.15

 Slug

-0.15

Nano

-0.14

 knee

-0.14

æ¤į

-0.13

Ø°Ø±

-0.13

clave

-0.13

wig

-0.13

POSITIVE LOGITS

vale

0.17

 Rhodes

0.15

AMED

0.15

cul

0.15

ogens

0.14

 ==============================================================

0.14

Ð¾ÑĢÐ¾Ð¼

0.14

aison

0.14

ored

0.14

-submit

0.14

Activations Density 0.002%

the name "Marion" and variations of its suffixes or forms

No Comments

No Known Activations