INDEX

Explanations

specific terms and identifiers related to scientific or mathematical notation and formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

illo

-0.16

á»Ľt

-0.15

illin

-0.15

ÑĸÑģÑĤ

-0.15

etric

-0.15

moth

-0.14

 Ð¿ÑĢÐ°Ð²Ð´Ð°

-0.14

 physical

-0.14

\\"

-0.14

ivil

-0.14

POSITIVE LOGITS

ukan

0.16

.Vertex

0.15

/REC

0.15

ìĥĿíĻľ

0.14

?>č↵

0.14

èħ

0.14

ovich

0.14

ereÃ§o

0.14

chet

0.14

Activations Density 0.096%

specific terms and identifiers related to scientific or mathematical notation and formatting

No Comments

No Known Activations