INDEX

Explanations

terms associated with distances traveled, particularly in transportation contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

usi

-0.16

spb

-0.15

usp

-0.14

bÃ©

-0.14

 Doub

-0.13

-bordered

-0.13

iant

-0.13

Pf

-0.13

 cres

-0.13

 camer

-0.13

POSITIVE LOGITS

 long

0.80

long

0.66

éķ¿

0.56

éķ·

0.56

 LONG

0.54

(long

0.53

.long

0.53

-long

0.51

LONG

0.51

 distance

0.49

Activations Density 0.090%

terms associated with distances traveled, particularly in transportation contexts

No Comments

No Known Activations