INDEX

Explanations

instances of people being quoted or cited in discussions

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

 Relevant

-0.16

 Humb

-0.16

att

-0.14

unsch

-0.14

 Powered

-0.14

annis

-0.14

 Parks

-0.14

 Giles

-0.13

 mini

-0.13

amilia

-0.13

POSITIVE LOGITS

 added

0.25

added

0.19

 ajout

0.18

-added

0.18

 said

0.16

 Added

0.16

åı¦

0.16

 further

0.15

Added

0.15

 ayrÄ±ca

0.15

Activations Density 0.033%

instances of people being quoted or cited in discussions

No Comments

No Known Activations