INDEX

Explanations

instances of the word "known" and its variations to indicate fame or recognition

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

toa

-0.16

il

-0.16

pie

-0.16

ocha

-0.15

ements

-0.15

saw

-0.14

ement

-0.14

emit

-0.14

gin

-0.14

arov

-0.14

POSITIVE LOGITS

known

0.19

 known

0.18

 throughout

0.18

ahir

0.17

 equally

0.16

 PartialView

0.16

 among

0.16

 Known

0.16

ptune

0.15

 amongst

0.15

Activations Density 0.026%

instances of the word "known" and its variations to indicate fame or recognition

No Comments

No Known Activations