INDEX

Explanations

concepts related to authenticity and connection to history

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

-0.17

at

-0.16

ivo

-0.15

lick

-0.15

aba

-0.15

une

-0.15

ÙĪØ·

-0.14

ey

-0.14

zej

-0.14

 viá»ĩc

-0.14

POSITIVE LOGITS

 impact

0.21

impact

0.20

Impact

0.19

 meaning

0.18

 significance

0.18

 characteristics

0.17

 Impact

0.17

 relevance

0.16

 bearing

0.16

 appeal

0.16

Activations Density 0.244%

concepts related to authenticity and connection to history

No Comments

No Known Activations