INDEX

Explanations

references to variable names and property values in programming code

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

bara

-0.14

Wes

-0.14

etheless

-0.13

\Eloquent

-0.13

illas

-0.13

Ð°Ð½Ð³

-0.13

oldem

-0.13

 kles

-0.13

jspx

-0.13

orz

-0.13

POSITIVE LOGITS

 Kaynak

0.15

UIFont

0.14

ovich

0.14

Poe

0.14

oup

0.13

Ì£

0.13

 Telecom

0.13

 Reporter

0.13

acc

0.13

Ou

0.12

Activations Density 0.505%

references to variable names and property values in programming code

No Comments

No Known Activations