INDEX

Explanations

references to time and duration in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ãły

-0.18

iae

-0.16

 otherwise

-0.15

hma

-0.14

ãĥ«ãĥī

-0.13

phia

-0.13

ãĥ¼ãĥĸ

-0.13

 Otherwise

-0.13

Ã³l

-0.13

ucha

-0.13

POSITIVE LOGITS

 lately

0.30

 recently

0.28

always

0.26

 always

0.25

Always

0.25

æľĢè¿ĳ

0.25

 Recently

0.25

Recently

0.24

 sempre

0.24

 finally

0.24

Activations Density 0.359%

references to time and duration in various contexts

No Comments

No Known Activations