INDEX

Explanations

references to people or alumni in a context of searching or hoping for their return

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

aign

-0.17

asion

-0.15

ieren

-0.15

ModelProperty

-0.14

erosis

-0.14

 MÃľ

-0.14

essions

-0.14

lamaz

-0.14

antan

-0.14

ulance

-0.14

POSITIVE LOGITS

cy

0.18

 eventual

0.16

au

0.15

ddy

0.15

aday

0.15

 intermediate

0.15

 ìľ¡

0.15

ech

0.15

ctp

0.14

 Intermediate

0.14

Activations Density 0.003%

references to people or alumni in a context of searching or hoping for their return

No Comments

No Known Activations