INDEX

Explanations

user interactions and confirmations related to actions or options in a software application

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

enga

-0.16

ãĤīãģı

-0.16

abad

-0.15

iph

-0.15

ng

-0.15

 Fest

-0.15

lÃ½

-0.15

DIN

-0.15

nge

-0.15

fest

-0.14

POSITIVE LOGITS

oplevel

0.17

ØªØ§ÙĨ

0.16

 Åŀimdi

0.15

áº¡n

0.15

ogne

0.14

ayo

0.14

pletion

0.14

Compiler

0.13

 prostitutas

0.13

plier

0.13

Activations Density 0.016%

user interactions and confirmations related to actions or options in a software application

No Comments

No Known Activations