INDEX

Explanations

references to locations or geographic features in a transportation context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ahan

-0.16

 putas

-0.15

Ã¤n

-0.15

.Align

-0.15

BindingUtil

-0.14

umeric

-0.14

tec

-0.14

asers

-0.14

/functions

-0.14

ocale

-0.14

POSITIVE LOGITS

arcer

0.16

enÃŃ

0.15

IVAL

0.15

 Brew

0.14

unday

0.14

 brew

0.14

emetery

0.14

 Wool

0.14

 ç·¨

0.14

agate

0.14

Activations Density 0.048%

references to locations or geographic features in a transportation context

No Comments

No Known Activations