INDEX

Explanations

strings and characters used in programming syntax, particularly those related to object notation and attribute selectors

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

“

-0.19

ToProps

-0.16

 Â«

-0.15

 âĢŀ

-0.15

ninger

-0.15

uale

-0.14

oen

-0.14

)<<

-0.14

¿Ĳ

-0.13

 ãĢĮ

-0.13

POSITIVE LOGITS

mare

0.15

avy

0.15

ahoma

0.15

avery

0.15

 Jennings

0.14

 âķ

0.14

bsite

0.14

crease

0.14

ward

0.14

ahoo

0.14

Activations Density 0.073%

strings and characters used in programming syntax, particularly those related to object notation and attribute selectors

No Comments

No Known Activations