INDEX

Explanations

instances related to swimming and water activities

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

aille

-0.17

_frm

-0.15

aÅ¼

-0.14

adera

-0.14

 Inflate

-0.14

Ã¦r

-0.14

arious

-0.13

BRO

-0.13

 Kerr

-0.13

Ä±b

-0.13

POSITIVE LOGITS

 swimming

0.15

 Basin

0.15

 Swim

0.14

 ÑĢÐ°ÑģÑĤ

0.14

 Swimming

0.14

 basin

0.14

IGIN

0.14

ills

0.14

 Variable

0.14

Bas

0.14

Activations Density 0.020%

instances related to swimming and water activities

No Comments

No Known Activations