INDEX

Explanations

occurrences of specific data types in programming contexts, particularly strings

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

ett

-0.17

goo

-0.16

hazi

-0.16

lessly

-0.15

dal

-0.15

iks

-0.15

etro

-0.15

erty

-0.14

icina

-0.14

POSITIVE LOGITS

Î»Î¹

0.14

ker

0.14

kola

0.14

è³Ģ

0.13

ified

0.13

toDouble

0.13

.fromCharCode

0.13

KER

0.13

 Patton

0.13

 Brew

0.13

Activations Density 0.019%

occurrences of specific data types in programming contexts, particularly strings

No Comments

No Known Activations