INDEX

Explanations

discussions related to event planning and organization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

meld

-0.15

_nr

-0.14

_simps

-0.14

 Ð¿Ñĭ

-0.14

Svc

-0.14

ç·Ĵ

-0.13

Ú¯Ø°

-0.13

hydration

-0.13

 numOf

-0.13

Ã³Å¼

-0.13

POSITIVE LOGITS

word

0.16

ourt

0.15

_COD

0.15

 Dram

0.15

 Because

0.15

 lots

0.15

imli

0.15

Ïį

0.15

 pregn

0.14

words

0.14

Activations Density 0.159%

discussions related to event planning and organization

No Comments

No Known Activations