INDEX

Explanations

statements expressing opinions or evaluations about experiences and perceptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

inho

-0.18

ÐºÑĢÐ°

-0.17

oldemort

-0.17

 Ð²ÐµÐ´ÑĮ

-0.15

iddi

-0.15

 QUICK

-0.14

quia

-0.14

olland

-0.14

rrha

-0.14

ezier

-0.14

POSITIVE LOGITS

Prostit

0.15

Ã³ng

0.15

gan

0.14

rog

0.14

best

0.13

mostly

0.13

åĮ

0.13

ongs

0.13

anon

0.13

 fairly

0.13

Activations Density 0.231%

statements expressing opinions or evaluations about experiences and perceptions

No Comments

No Known Activations