INDEX

Explanations

instances of the word "bei," indicating a focus on locations or situations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

cai

-0.17

thal

-0.17

vale

-0.16

à¤¾à¤Ń

-0.16

Meh

-0.15

åĵ

-0.15

ODULE

-0.15

 Duel

-0.14

ine

-0.14

à¸Ľà¸£à¸°à¸ª

-0.14

POSITIVE LOGITS

outh

0.16

omination

0.15

ouro

0.15

ropol

0.14

ToF

0.14

ignum

0.14

Fra

0.14

umba

0.14

æ¡

0.14

ertest

0.14

Activations Density 0.007%

instances of the word "bei," indicating a focus on locations or situations

No Comments

No Known Activations