INDEX

Explanations

references to philosophy and philosophical concepts

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

 Vinci

-0.18

asa

-0.18

een

-0.16

oller

-0.16

asso

-0.16

ÐµÑĨ

-0.16

entai

-0.15

emp

-0.15

eenth

-0.15

pulse

-0.15

POSITIVE LOGITS

osoph

0.19

ically

0.17

cial

0.16

ibe

0.16

ical

0.16

/art

0.15

ippi

0.15

á»ģn

0.15

Hue

0.14

cope

0.14

Activations Density 0.020%

references to philosophy and philosophical concepts

No Comments

No Known Activations