INDEX

Explanations

actions and events happening over time, particularly in relation to individuals and their characteristics

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

wards

-0.18

 ná»¯a

-0.14

èĢĥ

-0.13

ically

-0.13

 Ø§ÙĤØ¯Ø§Ùħ

-0.13

ly

-0.13

 Ranch

-0.13

ubern

-0.13

cks

-0.12

 Jacob

-0.12

POSITIVE LOGITS

 Already

0.17

 already

0.17

Already

0.16

already

0.16

 however

0.16

hic

0.15

enha

0.15

pub

0.15

Ã¦k

0.15

Ø±ÛĮØ²

0.15

Activations Density 0.092%

actions and events happening over time, particularly in relation to individuals and their characteristics

No Comments

No Known Activations