INDEX

Explanations

specific terms or names related to geographic locations and landmarks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

aktu

-0.16

å¸¯

-0.15

drv

-0.15

Ð¾Ð»Ð½

-0.15

 fatt

-0.15

ieri

-0.15

Ø§Ø

-0.15

eka

-0.14

Ñĳ

-0.13

mys

-0.13

POSITIVE LOGITS

ensis

0.16

arent

0.14

 Jama

0.14

skÃ¡

0.14

eming

0.14

inte

0.13

elong

0.13

orse

0.13

IENTATION

0.13

ense

0.13

Activations Density 0.040%

specific terms or names related to geographic locations and landmarks

No Comments

No Known Activations

specific terms or names related to geographic locations and landmarks

No Comments

No Known Activations