INDEX

Explanations

positive feedback and suggestions related to cooking and recipes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ior

-0.17

 Khal

-0.16

idy

-0.14

 Schmidt

-0.14

zcze

-0.14

.shtml

-0.14

 gratuit

-0.14

Ð¾ÐºÐ¾Ð»

-0.14

 Cage

-0.13

POSITIVE LOGITS

 akka

0.17

kaar

0.16

Parcel

0.16

ereotype

0.15

inne

0.15

Dro

0.15

ammo

0.15

'gc

0.14

atha

0.14

/dir

0.14

Activations Density 0.093%

positive feedback and suggestions related to cooking and recipes

No Comments

No Known Activations