INDEX

Explanations

geographical locations and references to them in the context of various events or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

 erÃ³t

-0.16

angs

-0.14

egie

-0.14

 Clown

-0.14

Ã¥n

-0.14

ertain

-0.13

atem

-0.13

ä½

-0.13

atively

-0.13

unately

-0.13

POSITIVE LOGITS

ammer

0.15

é³´

0.15

Î¹Î»Î¿

0.15

 AndAlso

0.14

 Monetary

0.14

Ø´ØªØ±

0.14

á»¥

0.14

untu

0.14

ÑĥÐºÐ¾Ð²

0.13

halt

0.13

Activations Density 0.083%

geographical locations and references to them in the context of various events or situations

No Comments

No Known Activations