INDEX

Explanations

references to locations and movements within specific geographical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

adel

-0.19

former

-0.15

aria

-0.15

onic

-0.14

izona

-0.14

 lodged

-0.14

aea

-0.13

exus

-0.13

stateParams

-0.13

BSD

-0.13

POSITIVE LOGITS

New

0.15

NewItem

0.14

undi

0.14

Kam

0.13

 Shore

0.13

ovu

0.13

Ear

0.13

lam

0.13

'];?>"

0.13

/******/

0.13

Activations Density 0.080%

references to locations and movements within specific geographical contexts

No Comments

No Known Activations