INDEX

Explanations

instances of personal experiences or situations involving everyday mishaps

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ãĥ³ãĥĹ

-0.15

reator

-0.15

 unnatural

-0.15

webtoken

-0.15

oplay

-0.14

masked

-0.14

Navigator

-0.14

ãĤĴè¦ĭãĤĭ

-0.14

enco

-0.14

\<^

-0.14

POSITIVE LOGITS

 forget

0.35

å¿ĺ

0.34

 forgot

0.33

 forgetting

0.30

forgot

0.30

 accident

0.29

forget

0.28

 forgotten

0.28

 Forgot

0.26

 Forget

0.24

Activations Density 0.411%

instances of personal experiences or situations involving everyday mishaps

No Comments

No Known Activations