INDEX

Explanations

references to specific groups or types of entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

 ActionTypes

-0.16

ass

-0.15

erring

-0.14

 pÅĻist

-0.14

ÑĢÑĥÐ´

-0.14

ÅĻÃŃ

-0.14

ypad

-0.14

alue

-0.14

ess

-0.14

erton

-0.14

POSITIVE LOGITS

usa

0.17

å£«

0.16

usb

0.15

omatic

0.15

uby

0.14

StringValue

0.14

tones

0.14

#ad

0.14

Ã³Å¼

0.13

 grap

0.13

Activations Density 0.066%

references to specific groups or types of entities

No Comments

No Known Activations